Benchmark Almanac

CADGenBench

CADGenBench submission godela_godela-modernized-agentic_20261109-183706: Godela - Modernized Agentic 85.1% tops its leaderboard Claude Fable 5 45.1% leads the models we track
Claude Fable 5 45.1% leads since June 2026
Only in system cards

Agents construct CAD models from design prompts. The generation split is graded for executability and geometric correctness.

Made by
Mecado + Hugging Face
Released
May 2026
Kind
CAD models
Level
University
Scored
Checked automatically
Answers
Code
Strongest model tested
Claude Fable 5 #11 on the capability index
Last in a system card
September 2026
Last model added
September 2026
Scores refreshed
November 12th, 2026
918
Entries on its own leaderboard, 11 models we track
2
System cards report it, from 1 lab

CADGenBench submission godela_godela-modernized-agentic_20261109-183706: Godela - Modernized Agentic tops the leaderboard with 85.1%

Best score per entry from the benchmark's own leaderboard, read on November 12th, 2026. Where a model ran with several settings or harnesses, we keep its best. Names in gray aren't in our model list: fine-tunes, agent systems, products and older models. They don't count toward leaders. The best model we track is Claude Fable 5, at 45.1%.

Claude Fable 5 leads with 45.1%, claims included

Best score per model from every source, including labs’ own numbers and claims Epoch AI collected from reports and papers. Labs pick their own settings, so a claim can beat an independent run of the same model.

The newest model with a score here came out in June 2026, and nobody has tested a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:

918 entries. Scroll sideways for the rest.

  1. 85.1 CADGenBench submission godela_godela-modernized-agentic_20261109-183706: Godela - Modernized Agentic
  2. 85.1 CADGenBench submission standard-manufacturing-co_smc-harness-fable-5-2-max_20261111-165655: SMC Harness + Fable 5.2 Max
  3. 84.8 CADGenBench submission deeprd_deeprd-v2_20261011-092629: deeprd-v2
  4. 84.4 CADGenBench submission rexl2018_vextcad-vxl-agent-r1_20261107-142023: VextCAD VXL agent (r1)
  5. 83.7 CADGenBench submission deeprd_deeprd_20261011-060231: deeprd
  6. 83.5 CADGenBench submission muhammed-ikbal-arikan_arikan-siemens-nx-mcp-claude-opus-5-5_20261006-044721: Arikan_Siemens_NX_MCP + Claude Opus 5.5
  7. 83.2 CADGenBench submission nik6_cad-ai-v11-4_20261014-200204: CAD AI V11.4
  8. 83.0 CADGenBench submission pzfreo_build123d-mcp-0-3-85-mcp-server-claude-o_20260924-101549: build123d-mcp 0.3.85 MCP server + Claude Opus 5.5 (max effort) r2
  9. 82.9 CADGenBench submission nik6_cad-ai-v11-3_20261014-184426: CAD AI V11.3
  10. 82.9 CADGenBench submission nik6_cad-ai-v11-all81-four-editing-reruns-opu_20261014-151205: CAD AI V11 all81 four editing reruns (Opus5.5)
  11. 82.9 CADGenBench submission nik6_cad-ai-v11-all81-fresh149-rerun-opus5-5_20261014-164341: CAD AI V11 all81 fresh149 rerun (Opus5.5)
  12. 82.9 CADGenBench submission nik6_cad-ai-v11-2_20261014-180126: CAD AI V11.2
  13. 82.7 CADGenBench submission pzfreo_build123d-mcp-0-3-90-mcp-server-claude-o_20260926-100215: build123d-mcp 0.3.90 MCP server + Claude Opus 5.5 (max effort) R2.3
  14. 82.6 CADGenBench submission symge_symge-claude-opus-5-5-agentic-hybrid_20260926-113258: Symge - Claude Opus 5.5: agentic hybrid
  15. 82.4 CADGenBench submission mechanical-reasoning_mechanical-reasoning-astra-xhigh_20261016-220931: Mechanical Reasoning — Astra xhigh
  16. 82.4 CADGenBench submission pzfreo_build123d-mcp-0-3-86-mcp-server-claude-o_20260925-194429: build123d-mcp 0.3.86 MCP server + Claude Opus 5.5 (max effort) R2.2
  17. 82.2 CADGenBench submission mechanical-reasoning_mechanical-reasoning-astra-xhigh_20261017-024229: Mechanical Reasoning — Astra xhigh
  18. 82.2 CADGenBench submission nik6_cad-ai-v11-all81-four-checkpoint-repairs_20261014-021956: CAD AI V11 all81 four checkpoint repairs (Opus 5.5)
  19. 82.0 CADGenBench submission atomic_atomic-cad-v3_20261102-200731: Atomic CAD v3
  20. 81.8 CADGenBench submission pzfreo_build123d-mcp-0-3-90-claude-sonnet-5-5-m_20260929-151832: build123d MCP 0.3.90 + Claude Sonnet 5.5 (Max)
  21. 81.8 CADGenBench submission pzfreo_build123d-mcp-0-3-85-mcp-server-claude-o_20260924-093300: build123d-mcp 0.3.85 MCP server + Claude Opus 5.5 (max effort)
  22. 81.1 CADGenBench submission godela_godela_20260915-045120: Godela
  23. 80.7 CADGenBench submission nik6_cad-ai-v11-all-81-complete-opus-5-5_20261013-023932: CAD AI V11 all 81 complete (Opus 5.5)
  24. 80.6 CADGenBench submission xueqinglin_gpt-6-astra-claude-code-20260917-104819_20260917-025938: gpt-6-astra_claude-code_20260917-104819
  25. 80.5 CADGenBench submission pzfreo_build123d-mcp-0-3-84-mcp-server-claude-o_20260923-092859: build123d-mcp 0.3.84 MCP server + Claude Opus 5.5 (xhigh effort)
  26. 79.7 CADGenBench submission cadse_generation-v2-editing-brief-v2_20261112-175916: generation v2 + editing brief v2
  27. 79.2 CADGenBench submission anonymous_anon-all-1788919650-351ecb_20260909-020747: anon-all-1788919650-351ecb
  28. 78.1 CADGenBench submission cadse_v5-edits-full-run-v2-plus-31-built-edits_20261112-155101: v5 edits: full run v2 plus 31 built edits
  29. 76.9 CADGenBench submission nik6_cad-ai-v11-full-benchmark-opus-5-5_20261011-213229: CAD AI V11 full benchmark (Opus 5.5)
  30. 76.8 CADGenBench submission atomic_atomic-cad-v2_20261022-043132: Atomic CAD v2
  31. 76.8 CADGenBench submission atomic_atomic-cad-v2_20261022-072149: Atomic CAD v2
  32. 76.6 CADGenBench submission zone404mars_zone-404-mars-freecad-harness-claude-opu_20261112-145855: Zone 404 Mars Freecad harness + Claude Opus 5.5 xhigh
  33. 76.2 CADGenBench submission nik6_nik6-harness-v9-claude-opus-5-5-high-eff_20261001-233943: nik6-harness-v9 + Claude Opus 5.5 (high effort)
  34. 75.5 CADGenBench submission tracycui_gpt-6-astra-high-hf-baseline-with-build1_20261023-031459: GPT-6 Astra high HF baseline with build123d
  35. 75.2 CADGenBench submission pzfreo_claude-opus-5-5-xhigh-effort-official-ba_20260923-174740: Claude Opus 5.5 (xhigh effort), official baseline prompt
  36. 75.2 CADGenBench submission eren_symge-claude-opus-5-5_20260926-072929: Symge - Claude Opus 5.5
  37. 74.7 CADGenBench submission atomic_atomic-cad-v1_20261018-043044: Atomic CAD v1
  38. 73.1 CADGenBench submission rexl2018_vextor-vxl-agent-r6_20261106-141850: Vextor VXL agent (r6)
  39. 71.6 CADGenBench submission faber-ai_faber-ai-gpt6_20260906-132046: Faber AI - gpt6
  40. 71.5 CADGenBench submission pzfreo_build123d-mcp-0-3-85-dev0-with-gpt-6-ast_20260905-073202: build123d-mcp 0.3.85.dev0 with GPT-6 Astra (High)
  41. 71.3 CADGenBench submission wormo_build123d-mcp-0-3-85-dev0-gpt-6-astra-xh_20261030-034033: build123d-mcp-0.3.85.dev0-gpt-6-astra-xhigh-supplement-202-240-20261030
  42. 71.1 CADGenBench submission thomwolf_gpt-6-astra-high-cadgenbench-baseline-mi_20260909-144301: GPT-6 Astra (high) + CADGenBench baseline - missing retry 5
  43. 70.9 CADGenBench submission rexl2018_vextor-vxl-agent-r5_20261105-143509: Vextor VXL agent (r5)
  44. 70.5 CADGenBench submission modelcorp_baseline-astra-codex-low-v1_20260905-013922: baseline-astra-codex-low-v1
  45. 70.1 CADGenBench submission wormo_build123d-mcp-0-3-85-dev0-gpt-6-astra-xh_20261030-013513: build123d-mcp-0.3.85.dev0-gpt-6-astra-xhigh-fresh-20261029t074303z
  46. 69.3 CADGenBench submission arche-industries_smith_20260828-220305: Smith
  47. 69.0 CADGenBench submission pzfreo_build123d-mcp-0-3-85-dev0-opus-5-xhigh-r_20260905-125604: build123d MCP 0.3.85.dev0 — Opus 5 xhigh — recognition-guided editing
  48. 68.8 CADGenBench submission rexl2018_vextor-vxl-agent-r4_20261105-013443: Vextor VXL agent (r4)
  49. 67.7 CADGenBench submission pzfreo_pzfreo-opus5-xhigh-mcp-drawing-evidence-_20260814-072949: pzfreo-opus5-xhigh-mcp-drawing-evidence-gen49-edit32
  50. 66.8 CADGenBench submission andrii-pytel_daedalus-reader-agent-opus-high_20261023-074129: Daedalus - reader agent (opus, high)
  51. 66.7 CADGenBench submission cadse_v4-edits-full-run-v2-plus-9-built-edits-_20261112-145656: v4 edits: full run v2 plus 9 built edits and 18 unchanged editing inputs
  52. 66.2 CADGenBench submission mecado_astra-high-mecado-baseline-with-build123_20260921-202238: Astra high Mecado Baseline with Build123d
  53. 65.8 CADGenBench submission nik6_nik6-harness-c-v3_20260819-020220: nik6-harness-c-v3
  54. 65.2 CADGenBench submission webmesh_webmesh-v4_20261105-043522: WebMesh v4
  55. 64.3 CADGenBench submission nik6_nik6-harness-c-v2_20260818-031411: nik6-harness-c-v2
  56. 64.2 CADGenBench submission nataliya-shakhovska_daedalus-a4h-opus55-medium-r2_20261112-150429: daedalus-a4h-opus55-medium-r2
  57. 63.9 CADGenBench submission pzfreo_build123d-mcp-v0381-claude-opus-5-xhigh-_20260807-101147: build123d-mcp-v0381-claude-opus-5-xhigh-full-r6
  58. 63.7 CADGenBench submission modelcorp_baseline-astra-codex-low-v0_20260904-225835: baseline-astra-codex-low-v0
  59. 63.6 CADGenBench submission saysolid-adapted-hub-llc_saysolid-gpt-6-1-sol-exact-dataset-nativ_20261025-071859: SaySolid gpt-6.1-sol exact-dataset-native-inputs visual-critic worker 682232c8535e
  60. 63.6 CADGenBench submission saysolid-adapted-hub-llc_saysolid-gpt-6-1-sol-exact-dataset-nativ_20261025-145423: SaySolid gpt-6.1-sol exact-dataset-native-inputs visual-critic worker 682232c8535e
  61. 63.0 CADGenBench submission nataliya-shakhovska_daedalus-a4h-opus55-medium-r1_20261112-150227: daedalus-a4h-opus55-medium-r1
  62. 63.0 CADGenBench submission nataliya-shakhovska_daedalus-a4h-opus55-medium-r3_20261112-150542: daedalus-a4h-opus55-medium-r3
  63. 63.0 CADGenBench submission mecado_astra-xhigh-mecado-baseline-with-build12_20260921-201510: Astra xhigh Mecado Baseline with Build123d
  64. 62.9 CADGenBench submission andrii-pytel_daedalus-phased-pipeline-opus-medium_20261007-144742: Daedalus - phased pipeline (opus, medium)
  65. 62.7 CADGenBench submission rexl2018_vextor-vxl-agent-engine-0030ca21-r3_20261103-142422: Vextor VXL agent (engine 0030ca21, r3)
  66. 62.7 CADGenBench submission pzfreo_opus5-xhigh-official-baseline-prompt-nom_20260811-034944: opus5-xhigh-official-baseline-prompt-nomcp-complete-r1
  67. 62.6 CADGenBench submission andrii-pytel_daedalus-phased-pipeline-opus-high_20261023-105235: Daedalus - phased pipeline (opus, high)
  68. 62.6 CADGenBench submission andrii-pytel_daedalus-reader-agent-opus-medium_20261024-185917: Daedalus - reader agent (opus, medium)
  69. 62.1 CADGenBench submission andrii-pytel_daedalus-phased-pipeline-opus-medium-fin_20261018-191648: Daedalus - phased pipeline (opus, medium) - final r1
  70. 61.9 CADGenBench submission cadse_baseline-v3-full-run-v2-27-editing-input_20261112-130649: baseline v3: full run v2 + 27 editing inputs unchanged (no-op floor), Opus xhigh, shift 0.7 % on generation only
  71. 61.5 CADGenBench submission saysolid-adapted-hub-llc_saysolid-gpt-6-astra-edits-gpt-5-6-sol-e_20260916-012742: SaySolid gpt-6-astra (edits gpt-5.6-sol) exact-dataset-native-inputs worker ce6aa3128893
  72. 61.3 CADGenBench submission saysolid-adapted-hub-llc_saysolid-claude-opus-5-5-exact-dataset-n_20261013-180006: SaySolid claude-opus-5-5 exact-dataset-native-inputs worker d9fd87a7c343
  73. 61.2 CADGenBench submission saysolid-adapted-hub-llc_saysolid-gpt-6-1-sol-exact-dataset-nativ_20260930-020419: SaySolid gpt-6.1-sol exact-dataset-native-inputs worker 672ab9a3732b
  74. 61.1 CADGenBench submission saysolid-adapted-hub-llc_saysolid-gpt-6-1-sol-exact-dataset-nativ_20261023-192958: SaySolid gpt-6.1-sol exact-dataset-native-inputs worker 682232c8535e
  75. 61.1 CADGenBench submission nik6_nik6-harness-c-v1_20260816-183610: nik6-harness-c-v1
  76. 60.1 CADGenBench submission andrii-pytel_daedalus-reader-wholesheet-ablation-opus_20261024-230348: daedalus-reader-wholesheet-ablation-opus-medium
  77. 60.0 CADGenBench submission saysolid-adapted-hub-llc_saysolid-gpt-6-1-sol-exact-dataset-nativ_20261008-110521: SaySolid gpt-6.1-sol exact-dataset-native-inputs worker 04d40445ddc3
  78. 59.9 CADGenBench submission saysolid-adapted-hub-llc_saysolid-gpt-6-1-sol-exact-dataset-nativ_20261104-222118: SaySolid gpt-6.1-sol exact-dataset-native-inputs worker 545fa00b8179
  79. 59.3 CADGenBench submission andrii-pytel_daedalus-phased-pipeline-opus-medium_20261024-185836: Daedalus - phased pipeline (opus, medium)
  80. 58.7 CADGenBench submission matthew-lieb_cadi-generation-and-editing-2026-09-19_20260920-153059: CADI generation and editing, 2026-09-19
  81. 57.9 CADGenBench submission pzfreo_build123d-mcp-0-3-84-dev0-gemini-3-8-fla_20260904-032010: build123d-mcp-0.3.84.dev0-gemini-3.8-flash-high-repair-first-complete81-r2
  82. 57.5 CADGenBench submission rexl2018_vextor-vxl-agent-engine-4cd1e674-r2_20261102-163559: Vextor VXL agent (engine 4cd1e674, r2)
  83. 57.5 CADGenBench submission xueqinglin_openai-gpt-5-6-sol-claude-code-20260827-_20260827-063801: openai.gpt-5.6-sol_claude-code_20260827-114734
  84. 57.4 CADGenBench submission nik6_nik6-cadgenbench-v1_20260808-223843: nik6-cadgenbench-v1
  85. 57.4 CADGenBench submission nik6_nik6-cadgenbench-v1_20260808-231147: nik6-cadgenbench-v1
  86. 57.3 CADGenBench submission rexl2018_vextor-vxl-agent-engine-4cd1e674_20261102-150618: Vextor VXL agent (engine 4cd1e674)
  87. 56.9 CADGenBench submission nik6_nik6-harness-v8-v1_20260831-043302: nik6-harness-v8-v1
  88. 56.6 CADGenBench submission pzfreo_build123d-mcp-0-3-84-dev0-gemini-3-8-fla_20260904-034650: build123d-mcp-0.3.84.dev0-gemini-3.8-flash-high-recognition-execution-gen-dev388-complete81-r2
  89. 56.1 CADGenBench submission pzfreo_build123d-mcp-0-3-84-dev388-gemini-3-8-f_20260903-075326: build123d-mcp-0.3.84.dev388-gemini-3.8-flash-high
  90. 55.9 CADGenBench submission pzfreo_build123d-mcp-0-3-84-dev0-gemini-3-8-fla_20260903-141226: build123d-mcp-0.3.84.dev0-gemini-3.8-flash-high-recognition-forced-editing-gen-dev388-complete81-r1
  91. 55.8 CADGenBench submission xueqinglin_claude-opus-5-claude-code-20260825-17400_20260825-095149: claude-opus-5_claude-code_20260825-174002
  92. 55.7 CADGenBench submission experiment_experiment_20260923-134635: Experiment
  93. 55.0 CADGenBench submission saysolid-adapted-hub-llc_saysolid-gpt-6-astra-exact-dataset-nativ_20260905-170835: SaySolid gpt-6-astra exact-dataset-native-inputs worker f4566f7b5661
  94. 54.9 CADGenBench submission b-rat_agent-cad-harness-claude-fable-5-1-gen49_20261012-002331: agent-cad harness / Claude Fable 5.1 (gen49 + edit32)
  95. 54.4 CADGenBench submission andrii-pytel_daedalus-single-react-agent-opus-medium_20261004-190209: Daedalus - single ReAct agent (opus, medium)
  96. 53.9 CADGenBench submission xueqinglin_openai-gpt-5-6-sol-baseline-20260826-193_20260826-115643: openai.gpt-5.6-sol_baseline_20260826-193928
  97. 53.7 CADGenBench submission cadgenbench-2d-to-3d_gpt-6-1-sol-agentic-baseline_20261012-111954: gpt-6.1-sol agentic baseline
  98. 53.3 CADGenBench submission andrii-pytel_daedalus-single-react-agent-opus-medium-_20261017-111238: Daedalus - single ReAct agent (opus, medium) - run 3
  99. 53.2 CADGenBench submission pzfreo_gpt-5-6-sol-xhigh-floor-chain-v0379_20260717-045810: gpt-5.6-sol-xhigh-floor-chain-v0379
  100. 53.0 CADGenBench submission andrii-pytel_daedalus-single-react-agent-opus-medium-_20261017-105639: Daedalus - single ReAct agent (opus, medium) - run 2
  101. 52.1 CADGenBench submission mecado_grok-4-7-xhigh-mecado-baseline-with-buil_20260921-210958: Grok 4.7 xhigh Mecado Baseline with Build123d
  102. 51.7 CADGenBench submission origogk_origogk-r24-convex-faces-remodels-108-11_20261019-142941: OrigoGK r24 convex faces + remodels 108 112 116 118 119 132 134 138 145
  103. 51.1 CADGenBench submission cadse_brief-v7-full-run-49-generation-parts-op_20261112-180052: brief v7 full run, 49 generation parts, Opus builder
  104. 50.8 CADGenBench submission pzfreo_build123d-mcp-0-3-83-gemini-flash-3-7_20260902-022750: build123d-mcp-0.3.83-gemini-flash-3.7
  105. 50.7 CADGenBench submission satvik-adyanthaya_archie-in-forge_20260711-184330: Archie in Forge
  106. 50.6 CADGenBench submission anonymous_anonymous-agent_20260914-123111: Anonymous agent
  107. 50.4 CADGenBench submission anon-12345_generation-editing_20261015-144308: generation-editing
  108. 49.8 CADGenBench submission experiment_experiment_20260822-234139: Experiment
  109. 49.8 CADGenBench submission modelcorp_baseline-astra-codex-medium-single-sessi_20260904-202625: baseline_astra_codex_medium_single_session
  110. 49.8 CADGenBench submission modelcorp_baseline-astra-codex-sequential-pass_20260904-201609: baseline_astra_codex_sequential_pass
  111. 49.7 CADGenBench submission anonymous_anon-gen-1788896800-17b078_20260908-194644: anon-gen-1788896800-17b078
  112. 49.6 CADGenBench submission mecado_grok-4-7-high-mecado-baseline-with-build_20260921-211028: Grok 4.7 high Mecado Baseline with Build123d
  113. 49.5 CADGenBench submission cadse_full-run-v2-49-parts-all-opus-xhigh-full_20261112-123301: full run v2: 49 parts, all Opus xhigh, full brief + principles + hole rules v2, shift 0.7 %
  114. 49.5 CADGenBench submission anonymous_anon-gen-1789061429-b7ed34_20260910-175227: anon-gen-1789061429-b7ed34
  115. 49.4 CADGenBench submission experiment_experiment_20260913-202641: Experiment
  116. 49.4 CADGenBench submission xueqinglin_baseline-gpt-5-6-sol-build123d_20260819-035800: baseline_gpt-5.6-sol_build123d
  117. 49.4 CADGenBench submission xueqinglin_baseline-gpt-5-6-sol-build123d_20260819-062918: baseline_gpt-5.6-sol_build123d
  118. 49.0 CADGenBench submission anonymous_test-submission-format_20260904-192600: test_submission_format
  119. 48.6 CADGenBench submission cadse_full-run-v1-49-parts-full-brief-principl_20261112-115103: full run v1: 49 parts, full brief + principles + hole rules v2, Opus builder (xhigh for 9 fixtures and 21 others), shift 0.7 %
  120. 48.5 CADGenBench submission makinarocks_drawx-2d3d-v4-gpt-6-astra_20261025-100833: drawx 2d3d v4 (gpt-6-astra)
  121. 48.4 CADGenBench submission w1ne_kernelcad-dev-refresh-20261026_20261026-192821: kernelcad-dev-refresh-20261026
  122. 48.4 CADGenBench submission anonymous_anonymous-agent_20260914-095345: Anonymous agent
  123. 47.9 CADGenBench submission anonymous_deskwright-gpt-5-5-xhigh-native-inline_20260830-182813: DeskWright GPT-5.5 xhigh native-inline
  124. 47.6 CADGenBench submission anon-12345_generation-editing_20261015-002847: generation-editing
  125. 47.5 CADGenBench submission w1ne_kernelcad-7e9082ab-gpt-5-6-sol-xhigh_20261019-105100: kernelcad-7e9082ab-gpt-5.6-sol-xhigh
  126. 47.4 CADGenBench submission saysolid-adapted-hub-llc_saysolid-gpt-6-astra-exact-dataset-nativ_20260914-192424: SaySolid gpt-6-astra exact-dataset-native-inputs generation-arm-only worker 08f43e775f98
  127. 47.0 CADGenBench submission origogk_origogk-r23-simplified-export-remodels-1_20261004-210724: OrigoGK r23 simplified export + remodels 112 118 119 134
  128. 46.8 CADGenBench submission anon-12345_generation-editing_20261013-140852: generation-editing
  129. 46.7 CADGenBench submission xueqinglin_glm-5-3-flash-claude-code-20260908-22435_20260909-022803: glm-5.3-flash_claude-code_20260908-224350
  130. 46.7 CADGenBench submission rouan_cadrs-claude-opus-5-5-mcp-hand-driven-r2_20261010-090115: cadrs + Claude Opus 5.5 (MCP, hand-driven) r2
  131. 46.3 CADGenBench submission xueqinglin_claude-opus-5-baseline-20260820-194627_20260820-115133: claude-opus-5_baseline_20260820-194627
  132. 46.1 CADGenBench submission pzfreo_gpt55-v0368-xhigh-full_20260706-050450: gpt55-v0368-xhigh-full
  133. 46.1 CADGenBench submission pzfreo_gpt55-v0366-xhigh-full-vtkfix_20260704-200116: gpt55-v0366-xhigh-full-vtkfix
  134. 46.0 CADGenBench submission pzfreo_pzfreo-gpt55-v0376-xhigh-full_20260709-181849: pzfreo-gpt55-v0376-xhigh-full
  135. 45.8 CADGenBench submission makinarocks_drawx-2d3d-v4-gpt-6-1-sol_20261025-051216: drawx 2d3d v4 (gpt-6.1-sol)
  136. 45.7 CADGenBench submission pzfreo_gpt-5-5-build123d-mcp-0-3-59-xhigh-r5_20260627-141619: gpt-5.5-build123d-mcp-0.3.59-xhigh-r5
  137. 45.5 CADGenBench submission xueqinglin_openai-gpt-5-6-sol-claude-code-20260825-_20260825-055902: openai.gpt-5.6-sol_claude-code_20260825-114538
  138. 45.4 CADGenBench submission andrii-pytel_daedalus-one-shot-script-opus-medium-run_20261017-111400: Daedalus - one-shot script (opus, medium) - run 3
  139. 45.3 CADGenBench submission arche_smith_20260711-010918: Smith
  140. 45.2 CADGenBench submission pzfreo_gpt-5-5-b123d-mcp-0-3-59-xhigh-full-p1_20260701-223602: gpt-5.5-b123d-mcp-0.3.59-xhigh-full-P1
  141. 45.1 Claude Fable 5
  142. 45.0 CADGenBench submission jspark_gpt-5-6-sol-build123d-loop-2_20260824-032415: gpt-5.6-sol_build123d_loop_2
  143. 45.0 CADGenBench submission anon-12345_generation-editing_20261003-134956: generation-editing
  144. 44.7 CADGenBench submission james-dillard_claude-opus-5-5-candidate-p-pi-harness-s_20261002-094853: Claude Opus 5.5 Candidate P (Pi harness, standard help, 2026-10-01)
  145. 44.5 CADGenBench submission pzfreo_gpt-5-5-build123d-mcp-0-3-57-xhigh_20260624-051501: gpt-5.5-build123d-mcp-0.3.57-xhigh
  146. 44.5 CADGenBench submission saysolid-adapted-hub-llc_saysolid-gpt-5-6-sol-exact-dataset-nativ_20260829-132038: SaySolid gpt-5.6-sol exact-dataset-native-inputs worker 4af68790c698
  147. 44.4 CADGenBench submission xueqinglin_kimi-k3-claude-code-20260907-214127_20260908-125546: kimi-k3_claude-code_20260907-214127
  148. 44.4 CADGenBench submission mecado_grok-4-6-high-mecado-baseline-with-build_20260813-210045: Grok 4.6 high Mecado Baseline with Build123d
  149. 43.9 CADGenBench submission pzfreo_gpt55-v0364-xhigh-full-verifyspec_20260704-055230: gpt55-v0364-xhigh-full-verifyspec
  150. 43.8 CADGenBench submission origogk_origogk-r22-edit-operators-208-217-218-2_20261004-051610: OrigoGK r22 edit operators 208 217 218 224 248
  151. 43.6 CADGenBench submission daanderson_fs-mcp-fable-5-minimal-harness_20260706-113645: FS MCP - Fable 5 - Minimal Harness
  152. 43.6 CADGenBench submission xueqinglin_dashscope-qwen3-8-max-baseline-20260820-_20260820-075059: dashscope.qwen3.8-max_baseline_20260820-152330
  153. 43.6 CADGenBench submission andrii-pytel_daedalus-one-shot-script-opus-medium_20261004-184853: Daedalus - one-shot script (opus, medium)
  154. 43.6 CADGenBench submission test-submission_browser-based-cad-agent-full-81-sample-r_20260904-223403: Browser-based CAD agent — full 81-sample run
  155. 43.2 CADGenBench submission mecado_claude-opus-5-max-mecado-baseline-with-b_20260813-223230: Claude Opus 5 max Mecado Baseline with Build123d
  156. 43.2 CADGenBench submission xueqinglin_dashscope-qwen3-8-max-claude-code-202608_20260826-113028: dashscope.qwen3.8-max_claude-code_20260826-192133
  157. 43.1 CADGenBench submission xueqinglin_openai-gpt-5-6-sol-baseline-20260820-184_20260820-112107: openai.gpt-5.6-sol_baseline_20260820-184227
  158. 43.0 CADGenBench submission makinarocks_drawx-2d3d-v53-gpt-6-1-terra_20261027-061524: drawx 2d3d v53 (gpt-6.1-terra)
  159. 43.0 CADGenBench submission jspark_gpt-5-6-sol-build123d_20260717-074106: gpt-5.6-sol build123d
  160. 42.8 CADGenBench submission paul-fremantle-pzfreo_build123d-mcp-claude-opus-4-8-full-81-fi_20260621-073422: build123d-mcp + Claude Opus 4.8 (full, 81 fixtures)
  161. 42.7 CADGenBench submission saysolid-adapted-hub-llc_saysolid-gpt-5-6-sol-exact-dataset-nativ_20260829-225405: SaySolid gpt-5.6-sol exact-dataset-native-inputs worker 4af68790c698
  162. 42.7 CADGenBench submission pzfreo_claude-opus-4-8-build123d-mcp-0-3-56_20260622-220357: claude-opus-4.8-build123d-mcp-0.3.56
  163. 42.7 CADGenBench submission pzfreo_pzfreo_20260622-205211: pzfreo
  164. 42.5 CADGenBench submission saysolid-adapted-hub-llc_saysolid-gpt-5-6-sol-exact-dataset-nativ_20260902-143854: SaySolid gpt-5.6-sol exact-dataset-native-inputs worker 364c948f664d
  165. 42.5 CADGenBench submission rouan_cadrs-claude-opus-5-5-mcp-hand-driven_20261010-040826: cadrs + Claude Opus 5.5 (MCP, hand-driven)
  166. 42.4 CADGenBench submission mecado_grok-4-6-xhigh-mecado-baseline-with-buil_20260813-215410: Grok 4.6 xhigh Mecado Baseline with Build123d
  167. 42.3 CADGenBench submission saysolid-adapted-hub-llc_saysolid-gpt-5-6-sol-exact-dataset-nativ_20260829-181641: SaySolid gpt-5.6-sol exact-dataset-native-inputs worker 4af68790c698
  168. 42.3 CADGenBench submission saysolid-adapted-hub-llc_saysolid-gpt-5-6-sol-exact-dataset-nativ_20260829-080934: SaySolid gpt-5.6-sol exact-dataset-native-inputs worker 464ef83f8531
  169. 42.1 CADGenBench submission pzfreo_gpt-5-6-sol-medium-mcp-0-3-78_20260711-055408: gpt-5.6-sol-medium-mcp-0.3.78
  170. 42.0 CADGenBench submission andrii-pytel_daedalus-one-shot-script-opus-medium-run_20261017-111318: Daedalus - one-shot script (opus, medium) - run 2
  171. 41.5 CADGenBench submission xueqinglin_openai-gpt-5-6-sol-baseline-20260825-111_20260825-033327: openai.gpt-5.6-sol_baseline_20260825-111524
  172. 41.2 CADGenBench submission mecado_gpt-5-6-sol-xhigh-mecado-baseline-with-b_20260813-233018: GPT-5.6 Sol xhigh Mecado Baseline with Build123d
  173. 41.1 CADGenBench submission pzfreo_gpt-5-5-build123d-mcp-0-3-56-v2_20260623-161750: gpt-5.5-build123d-mcp-0.3.56-v2
  174. 41.1 CADGenBench submission pzfreo_gpt-5-5-build123d-mcp-0-3-59-medium-r2_20260627-143151: gpt-5.5-build123d-mcp-0.3.59-medium-r2
  175. 41.1 CADGenBench submission michaelr27_gpt-5-6-sol-hf-baseline-with-build123d_20260713-183956: GPT-5.6 Sol HF Baseline with Build123d
  176. 40.8 CADGenBench submission saysolid-adapted-hub-llc_saysolid-gpt-5-6-sol-exact-dataset-nativ_20260902-063145: SaySolid gpt-5.6-sol exact-dataset-native-inputs worker 364c948f664d
  177. 40.8 CADGenBench submission anonymous_anon-gen-1788841910-f09d41_20260908-043152: anon-gen-1788841910-f09d41
  178. 40.7 CADGenBench submission bolev-mikhail_b2c-opus5-finish-v2-gen49_20260916-113951: b2c-opus5-finish-v2-gen49
  179. 40.6 CADGenBench submission dani2l_build123d-mcp-0-3-91-sonnet-5-5_20261029-043937: build123d-mcp-0.3.91-sonnet-5.5
  180. 40.5 CADGenBench submission anon-12345_generation_20260930-134942: generation
  181. 40.2 CADGenBench submission saysolid-adapted-hub-llc_saysolid-gpt-5-6-sol-exact-dataset-nativ_20260902-201006: SaySolid gpt-5.6-sol exact-dataset-native-inputs worker 364c948f664d
  182. 40.2 CADGenBench submission origogk_origogk-r21-pinched-sliver-repair-240_20261001-033654: OrigoGK r21 pinched sliver repair 240
  183. 39.8 CADGenBench submission jspark_gpt-5-6-sol-cadquery-max-iter5_20260712-145235: gpt-5.6-sol cadquery max-iter5
  184. 39.5 CADGenBench submission origogk_origogk-r20-face-extrusions-209-211-240_20261001-021200: OrigoGK r20 face extrusions 209 211 240
  185. 39.4 CADGenBench submission anonymous_anon-gen-1787944336-7ffd_20260828-191217: anon-gen-1787944336-7ffd
  186. 39.4 CADGenBench submission anonymous_anon-gen-1787928380-e027_20260828-144621: anon-gen-1787928380-e027
  187. 39.1 CADGenBench submission anon-12345_generation_20260929-041603: generation
  188. 38.8 CADGenBench submission unifyh_opus-48-toy-plugin-run4_20260709-031252: opus-48-toy-plugin-run4
  189. 38.7 GPT-5.5 Pro
  190. 38.7 CADGenBench submission jselstad_opus-4-8-claude-code-text-to-cad-skill_20260618-075019: Opus 4.8 — Claude Code + text-to-cad skill
  191. 38.2 CADGenBench submission anonymous_anon-gen-1787893554-7a60_20260828-050555: anon-gen-1787893554-7a60
  192. 37.9 CADGenBench submission origogk_origogk-r19-hole-removal-205_20260930-125014: OrigoGK r19 hole removal 205
  193. 37.8 CADGenBench submission arche_smith_20260710-221438: Smith
  194. 37.6 CADGenBench submission anonymous_anon-gen-1787884326-48c4_20260828-023207: anon-gen-1787884326-48c4
  195. 37.5 CADGenBench submission anonymous_anon-gen-1787868852-149a_20260827-221413: anon-gen-1787868852-149a
  196. 37.0 CADGenBench submission mecado_grok-4-5-high-mecado-baseline-with-build_20260813-203342: Grok 4.5 high Mecado Baseline with Build123d
  197. 36.9 Claude Opus 4.7
  198. 36.8 CADGenBench submission min-liu_chamfer-cad-agent-from-smartai_20260705-213856: Chamfer-CAD agent from SmartAI
  199. 36.7 CADGenBench submission test_test-submission_20260702-031247: test submission
  200. 36.7 CADGenBench submission bolev-mikhail_b2c-opus5-tools-gen49_20260910-122220: b2c-opus5-tools-gen49
  201. 36.6 CADGenBench submission origogk_origogk-r15-sliver-repair-250_20260930-105932: OrigoGK r15 sliver repair 250
  202. 36.4 CADGenBench submission jselstad_opus-4-8-claude-code-build123d-mcp_20260618-080918: Opus 4.8 — Claude Code + build123d-mcp
  203. 36.4 CADGenBench submission anon-12345_generation_20260928-152617: generation
  204. 36.0 GPT-5.5
  205. 35.9 CADGenBench submission unifyh_opus-48-toy-plugin-run3_20260703-060749: opus-48-toy-plugin-run3
  206. 35.9 CADGenBench submission unifyh_opus-48-toy-plugin-run2_20260703-024748: opus-48-toy-plugin-run2
  207. 35.8 CADGenBench submission chow_20260902-114129-muse-spark-full_20260903-154026: 20260902_114129_muse-spark_full
  208. 35.8 CADGenBench submission anonymous_anon-gen-1787797492-bb9e_20260827-022453: anon-gen-1787797492-bb9e
  209. 35.7 CADGenBench submission origogk_origogk-r14-face-offsets-231-250_20260930-100641: OrigoGK r14 face offsets 231 250
  210. 35.3 CADGenBench submission nataliya-shakhovska_daedalus-a4h-nogate-opus55-medium-r1_20261111-115811: daedalus-a4h-nogate-opus55-medium-r1
  211. 35.2 CADGenBench submission nataliya-shakhovska_daedalus-a4h-nogate-opus55-medium-r3_20261112-145445: daedalus-a4h-nogate-opus55-medium-r3
  212. 35.1 CADGenBench submission nrocketmann_glm-5-3-max-agentic-cad-zcode-subagents-_20260903-065136: GLM-5.3-Max agentic CAD (ZCode subagents, build123d)
  213. 34.9 CADGenBench submission jselstad_opus-4-8-claude-code-basic-no-mcp-skill_20260618-071847: Opus 4.8 — Claude Code (basic, no MCP/skill)
  214. 34.6 CADGenBench submission reckless-lampshade-230826_gpt-5-6-combined-best-generation_20260823-174609: gpt 5.6 combined best generation
  215. 34.6 CADGenBench submission nataliya-shakhovska_daedalus-a4h-notable-opus55-medium-r1_20261111-123643: daedalus-a4h-notable-opus55-medium-r1
  216. 34.5 Claude Opus 4.8
  217. 34.5 CADGenBench submission origogk_origogk-r13-partial-238-thickness-edit_20260930-050126: OrigoGK r13 partial 238 thickness edit
  218. 34.4 CADGenBench submission nataliya-shakhovska_daedalus-a4h-nogate-opus55-medium-r2_20261112-144806: daedalus-a4h-nogate-opus55-medium-r2
  219. 34.3 CADGenBench submission shashwatsaxena136_opus-4-8-build123d-baseline-full-81_20260615-171912: Opus 4.8 build123d baseline (full 81)
  220. 34.2 CADGenBench submission pzfreo_build123d-mcp-0-3-90-gemini-4-argon-high_20261022-124342: build123d-mcp-0.3.90-gemini-4-argon-high
  221. 34.0 CADGenBench submission james-dillard_gpt-6-luna-candidate-n-pi-harness-five-s_20261002-094803: GPT-6 Luna Candidate N (Pi harness, five-stage workflow, 2026-10-01)
  222. 34.0 CADGenBench submission nataliya-shakhovska_daedalus-a4h-notable-opus55-medium-r3_20261112-145541: daedalus-a4h-notable-opus55-medium-r3
  223. 34.0 CADGenBench submission origogk_origogk-r12-remove-faces-edit-128-closed_20260930-033916: OrigoGK r12 remove-faces edit + 128 closed slots
  224. 33.9 CADGenBench submission jselstad_opus-4-8-claude-code-build123d-mcp_20260617-144101: Opus 4.8 — Claude Code + build123d-mcp
  225. 33.9 CADGenBench submission gpt-code_glm-5-3-flash-cadgenbench-baseline_20260831-100955: GLM-5.3-Flash CADGenBench baseline
  226. 33.9 CADGenBench submission hermes-agent_cadqueryskills-hermes-gpt-5-6-luna_20260921-191629: CadQuerySkills + Hermes + GPT-5.6-Luna
  227. 33.7 CADGenBench submission nataliya-shakhovska_daedalus-a4h-notable-opus55-medium-r2_20261112-145255: daedalus-a4h-notable-opus55-medium-r2
  228. 33.5 CADGenBench submission fuhao_opencode-qwen3-8-max-2d-to-3d-plugin-0-7_20261108-070837: opencode + qwen3.8-max · 2d-to-3d plugin 0.7.7.2-dev3
  229. 33.0 CADGenBench submission fuhao_opencode-qwen3-8-max-baseline-no-plugin_20261108-065450: opencode + qwen3.8-max · baseline (no plugin)
  230. 32.9 CADGenBench submission anonymous_anon-gen-1787778946-d6ad_20260826-211548: anon-gen-1787778946-d6ad
  231. 32.9 CADGenBench submission james-dillard_gpt-6-luna-candidate-m-pi-harness-contro_20261002-094716: GPT-6 Luna Candidate M (Pi harness, control help, 2026-10-01)
  232. 32.9 CADGenBench submission james-dillard_gpt-5-6-sol-candidate-g-pi-harness-2026-_20260831-091037: GPT-5.6 Sol Candidate G (Pi harness, 2026-08-28)
  233. 32.8 CADGenBench submission shean-rahman_kinth-cadgenbench-full-gpt-5-5-retry-3_20260630-181939: Kinth CADGenBench full gpt-5.5 retry 3
  234. 32.8 CADGenBench submission origogk_origogk-r10-sparse-first-voxel-fallback_20260930-011452: OrigoGK r10 sparse-first voxel-fallback
  235. 32.7 CADGenBench submission james-dillard_gpt-5-6-sol-candidate-f-pi-harness-2026-_20260831-091039: GPT-5.6 Sol Candidate F (Pi harness, 2026-08-28)
  236. 32.6 CADGenBench submission origogk_origogk-r11-128-drawn-diameter-source_20260930-015114: OrigoGK r11 128 drawn-diameter source
  237. 32.3 CADGenBench submission james-dillard_gpt-5-6-sol-candidate-i-pi-harness-2026-_20260901-211012: GPT-5.6 Sol Candidate I (Pi harness, 2026-09-01)
  238. 32.2 CADGenBench submission origogk_origogk-r9-voxel-first-sliver-free_20260929-235952: OrigoGK r9 voxel-first sliver-free
  239. 32.2 CADGenBench submission jselstad_opus-4-8-claude-code-basic-no-mcp-skill_20260617-141618: Opus 4.8 — Claude Code (basic, no MCP/skill)
  240. 31.6 CADGenBench submission anon-120824_gpt-5-6_20260812-043905: gpt 5.6
  241. 31.2 CADGenBench submission origogk_origogk-r7-reviewed-sources_20260929-233435: OrigoGK r7 reviewed-sources
  242. 31.1 CADGenBench submission origogk_origogk-r8-voxel-first_20260929-234724: OrigoGK r8 voxel-first
  243. 31.1 Gemini 3.1 Pro
  244. 30.9 Claude Opus 4.6
  245. 30.8 CADGenBench submission rakshit-dwivedi_proxima_20260903-035049: Proxima
  246. 30.7 CADGenBench submission nataliya-shakhovska_daedalus-a4h-whole-opus55-medium-r2_20261112-150703: daedalus-a4h-whole-opus55-medium-r2
  247. 30.5 CADGenBench submission mliu_chamfer-cad-harness-0-1-1_20260707-033749: chamfer-cad-harness-0.1.1
  248. 30.5 CADGenBench submission brambling_brambling_20260909-045047: brambling
  249. 30.4 CADGenBench submission anon-233107_eval-b12_20260912-051712: eval-b12
  250. 30.2 CADGenBench submission saysolid-adapted-hub-llc_saysolid-gpt-5-6-luna-exact-dataset-nati_20260826-080728: SaySolid gpt-5.6-luna exact-dataset-native-inputs worker 41bd4d911831
  251. 30.0 CADGenBench submission tharun-arety_cadrig-alpha_20260917-211434: CADRIG Alpha
  252. 30.0 CADGenBench submission cadsmith42_fable-5-1-agentic-editing-v2_20260913-185705: fable-5-1-agentic-editing-v2
  253. 30.0 CADGenBench submission nataliya-shakhovska_daedalus-a4h-whole-opus55-medium-r3_20261112-150821: daedalus-a4h-whole-opus55-medium-r3
  254. 29.9 CADGenBench submission anonymous_anon-edit-1787880475-69c8_20260828-012758: anon-edit-1787880475-69c8
  255. 29.8 CADGenBench submission xueqinglin_dashscope-qwen3-8-max-claude-code-202608_20260825-110841: dashscope.qwen3.8-max_claude-code_20260825-190219
  256. 29.8 CADGenBench submission nataliya-shakhovska_daedalus-a4h-whole-opus55-medium-r1_20261111-153840: daedalus-a4h-whole-opus55-medium-r1
  257. 29.7 CADGenBench submission tomuiv_mad-deepseek-v4-1-flash-baseline_20261003-120717: MAD DeepSeek-V4.1-Flash baseline
  258. 29.7 CADGenBench submission phi-linh_cad-gen-v4_20260817-150126: cad-gen v4
  259. 29.7 CADGenBench submission saysolid-adapted-hub-llc_saysolid-gpt-5-6-sol-exact-dataset-nativ_20260826-002817: SaySolid gpt-5.6-sol exact-dataset-native-inputs worker 41bd4d911831
  260. 29.6 CADGenBench submission pzfreo_gpt-5-5-build123d-mcp-0-3-56-partial61of_20260623-111130: gpt-5.5-build123d-mcp-0.3.56-partial61of81
  261. 29.6 CADGenBench submission origogk_origogk-r6-source-fix-edge-budget_20260929-170942: OrigoGK r6 source-fix edge-budget
  262. 29.6 CADGenBench submission pimbs_pimbsv1_20260901-191627: Pimbsv1
  263. 29.5 CADGenBench submission anonymous_anon-edit-1787868057-f965_20260827-220059: anon-edit-1787868057-f965
  264. 29.4 CADGenBench submission feral-teapot-230826_gpt-5-6_20260823-154940: gpt 5.6
  265. 29.4 CADGenBench submission origogk_origogk-full-denominator-automatic-run-2_20260927-125419: OrigoGK full denominator automatic run 20260927
  266. 29.2 CADGenBench submission anonymous_o-a1-1-f_20261021-142015: O-A1-1_f
  267. 28.9 CADGenBench submission anon-224918_sweep-g_20260911-054807: sweep-g
  268. 28.7 CADGenBench submission andrii-pytel_daedalus-single-react-agent-opus-medium_20261003-215209: Daedalus - single ReAct agent (opus, medium)
  269. 28.7 CADGenBench submission anonymous_anon-edit-1787797485-f5ff_20260827-022447: anon-edit-1787797485-f5ff
  270. 28.6 CADGenBench submission anonymous_anon-edit-1787780317-d743_20260826-213840: anon-edit-1787780317-d743
  271. 28.5 CADGenBench submission daanderson_fsmcp-opus-4-8_20260616-114515: FSMCP+Opus 4.8
  272. 28.5 CADGenBench submission quartz17_quartz17_20260909-013330: quartz17
  273. 28.3 CADGenBench submission arche_smith_20260702-225821: Smith
  274. 28.3 CADGenBench submission anonymous_anon-edi-1788896801-b000c8_20260908-194649: anon-edi-1788896801-b000c8
  275. 28.3 Claude Sonnet 4.6
  276. 28.3 CADGenBench submission joveh67_horu-8108_20261013-193641: horu-8108
  277. 28.0 CADGenBench submission metax_qwen-38-local-agent-union-73-81_20261012-063726: qwen-38 local agent (union 73/81)
  278. 27.9 CADGenBench submission andrii-pytel_daedalus-phased-pipeline-opus-medium_20261004-083406: Daedalus - phased pipeline (opus, medium)
  279. 27.9 CADGenBench submission saysolid-adapted-hub-llc_saysolid-kimi-k3-exact-dataset-native-in_20260827-183525: SaySolid kimi-k3 exact-dataset-native-inputs worker 3d74eda951f1
  280. 27.7 CADGenBench submission cal-b_cal-b_20260908-204810: cal-b
  281. 27.6 CADGenBench submission anonymous_anon-edi-1788841924-317e2e_20260908-043208: anon-edi-1788841924-317e2e
  282. 27.6 CADGenBench submission anonymous_g5b_20261026-140509: G5b
  283. 27.6 CADGenBench submission tohom76_lakare-6523_20261013-193625: lakare-6523
  284. 27.3 CADGenBench submission cadsmith42_fable-5-1-agentic-editing_20260913-081127: fable-5-1-agentic-editing
  285. 27.2 CADGenBench submission hureho60_zuniri-4618_20261013-193655: zuniri-4618
  286. 27.2 CADGenBench submission anonymous_run-d_20261030-132414: Run D
  287. 27.1 CADGenBench submission anonymous_run-j_20261106-092634: Run J
  288. 26.9 CADGenBench submission anonymous_o_20261108-175622: O
  289. 26.9 CADGenBench submission anonymous_test-submission_20260821-191118: test-submission
  290. 26.8 CADGenBench submission origogk_origogk-r5-contact-zero-rigid-edit_20260929-152629: OrigoGK r5 contact-zero rigid-edit
  291. 26.7 CADGenBench submission cal-a_cal-a_20260908-024134: cal-a
  292. 26.7 CADGenBench submission anonymous_run-l_20261107-122243: Run L
  293. 26.6 CADGenBench submission saysolid-adapted-hub-llc_saysolid-gpt-5-6-terra-exact-dataset-nat_20260826-024740: SaySolid gpt-5.6-terra exact-dataset-native-inputs worker 41bd4d911831
  294. 26.4 CADGenBench submission reify_reify-deepseek-low-asi-all-edit-32-01_20261026-082500: reify-deepseek-low-asi-all-edit-32-01
  295. 26.4 CADGenBench submission bruno-mutagent_mutagent-brepsmith-opus-5-xhigh-agentic-_20260828-132328: mutagent-brepsmith — Opus-5 xhigh agentic harness (editing-only)
  296. 26.2 CADGenBench submission cadybara-benchmark_exp005-run003-100-plus-copied-200_20260614-191528: EXP005 RUN003 100 plus copied 200
  297. 26.1 CADGenBench submission cadybara_exp005-run003-100-plus-copied-200_20260614-192416: EXP005 RUN003 100 plus copied 200
  298. 26.1 CADGenBench submission andrii-pytel_daedalus-one-shot-script-opus-medium_20261003-215858: Daedalus - one-shot script (opus, medium)
  299. 26.0 CADGenBench submission anonymous_run-g_20261105-082956: Run G
  300. 25.9 CADGenBench submission anonymous_cad-agent_20260821-172041: cad-agent
  301. 25.8 CADGenBench submission origogk_origogk-bounded-surface-diagnostic_20260927-182738: OrigoGK bounded surface diagnostic
  302. 25.8 CADGenBench submission origogk_origogk-planar-surface-diagnostic_20260927-160851: OrigoGK planar surface diagnostic
  303. 25.8 CADGenBench submission origogk_origogk-surface-quality-diagnostic_20260927-221023: OrigoGK surface quality diagnostic
  304. 25.7 CADGenBench submission w1ne_kernelcad-probe-genlane-v3-20261020_20261020-015604: kernelcad-probe-genlane-v3-20261020
  305. 25.6 CADGenBench submission stealth_stealth-harness-haiku-5-5-xhigh_20261022-003154: Stealth Harness + Haiku 5.5 xHigh
  306. 25.6 CADGenBench submission anonymous_run-f_20261103-081936: Run F
  307. 25.5 CADGenBench submission anonymous_v_20261110-144608: V
  308. 25.4 CADGenBench submission anonymous_run-h_20261105-161202: Run H
  309. 25.4 CADGenBench submission anonymous_p_20261109-044130: P
  310. 25.2 CADGenBench submission anonymous_run-i_20261106-041307: Run I
  311. 25.2 CADGenBench submission anonymous_v0-5_20261106-002457: v0.5
  312. 25.2 CADGenBench submission anonymous_q_20261109-090251: Q
  313. 25.0 CADGenBench submission origogk_origogk-retained-profile-surface-diagnos_20260927-050054: OrigoGK retained profile surface diagnostic
  314. 24.9 Gemini 3.1 Flash-Lite
  315. 24.6 CADGenBench submission niziz67_homit-6594_20261007-061132: homit-6594
  316. 24.6 CADGenBench submission rakshit-dwivedi_proxima_20260902-200639: Proxima
  317. 24.5 CADGenBench submission james-dillard_gpt-5-nano-candidate-l-pi-harness-five-s_20261001-001100: GPT-5 Nano Candidate L (Pi harness, five-stage workflow, 2026-09-30)
  318. 24.3 CADGenBench submission anonymous_r_20261109-113330: R
  319. 24.0 CADGenBench submission origogk_origogk-axial-step-edit-215-diagnostic_20260926-161403: OrigoGK axial STEP edit 215 diagnostic
  320. 23.9 CADGenBench submission anonymous_n_20261108-154638: N
  321. 23.8 CADGenBench submission miles-bimrose_qwen3-vl-235b-buil123d-ft-2stage_20260624-032814: Qwen3-VL-235B-buil123d-FT-2stage
  322. 23.8 CADGenBench submission anonymous_m_20261108-125233: M
  323. 23.7 CADGenBench submission anonymous_lq-1_20261108-121453: LQ_1
  324. 23.6 CADGenBench submission local-user_t046-cgb-merge-101-150-mixed-v1_20261026-114525: t046-cgb-merge-101-150-mixed-v1
  325. 23.6 CADGenBench submission miles-bimrose_qwen3-vl-235b-build123d-v6-lora-ckpt-150_20260618-225130: Qwen3-VL-235B build123d v6 (LoRA ckpt-15000)
  326. 23.6 CADGenBench submission jigem11_vomuko-4761_20261007-061022: vomuko-4761
  327. 23.5 CADGenBench submission anonymous_t_20261110-100802: T
  328. 23.4 CADGenBench submission anonymous_s_20261109-134515: S
  329. 23.4 CADGenBench submission xueqinglin_glm-5-2-baseline-20260820-170417_20260820-091506: glm-5.2_baseline_20260820-170417
  330. 23.3 CADGenBench submission anonymous_run-e_20261030-134619: Run E
  331. 23.2 CADGenBench submission anonymous_run-k_20261106-221903: Run K
  332. 22.9 CADGenBench submission origogk_origogk-sparse-suite-diagnostic_20260926-145739: OrigoGK sparse suite diagnostic
  333. 22.8 CADGenBench submission experiment_experiment_20260822-194005: Experiment
  334. 22.7 CADGenBench submission anonymous_run-c_20261030-144138: Run C
  335. 22.6 CADGenBench submission feorka44_indoin-5234_20261006-210352: indoin-5234
  336. 22.5 CADGenBench submission anonymous_s46-a1_20261025-150639: S46-A1
  337. 22.5 CADGenBench submission anonymous_run-b_20261030-140256: Run B
  338. 22.5 CADGenBench submission anonymous_s45-a1_20261021-131325: S45-A1
  339. 22.1 CADGenBench submission arpado79_kaar-e88c_20261006-220543: kaar-e88c
  340. 21.8 CADGenBench submission ulwior35_givein-5069_20261006-213142: givein-5069
  341. 21.7 CADGenBench submission miles-bimrose_qwen3-6-buil123d-ft-2stage_20260706-163128: Qwen3.6-buil123d-FT-2stage
  342. 21.7 CADGenBench submission james-dillard_gpt-5-nano-candidate-k-pi-harness-contro_20261001-022034: GPT-5 Nano Candidate K (Pi harness, control help, 2026-09-30)
  343. 21.6 CADGenBench submission miles-bimrose_drmstep-hybrid-v5_20260628-062259: drmstep-hybrid-v5
  344. 21.5 CADGenBench submission anonymous_u_20261110-121946: U
  345. 21.4 CADGenBench submission arche_smith_20260709-234450: Smith
  346. 21.4 CADGenBench submission arche_smith_20260624-022436: Smith
  347. 21.4 CADGenBench submission siwoh56_hesutu-6163_20261007-061147: hesutu-6163
  348. 21.3 CADGenBench submission anonymous_w_20261112-070217: W
  349. 21.2 CADGenBench submission anonymous_sa-v2_20261025-224542: SA-V2
  350. 20.9 CADGenBench submission arche_smith_20260710-214646: Smith
  351. 20.9 CADGenBench submission saysolid-adapted-hub-llc_saysolid-gpt-6-astra-exact-dataset-nativ_20260914-205657: SaySolid gpt-6-astra exact-dataset-native-inputs editing-arm-only worker 46e6708c4207
  352. 20.8 CADGenBench submission junde_junde-test_20260716-102222: junde-test
  353. 20.4 CADGenBench submission anonymous_v0-9_20261106-002525: v0.9
  354. 20.4 CADGenBench submission anonymous_v0-2_20261105-153348: v0.2
  355. 20.4 CADGenBench submission anonymous_v0-7_20261106-002511: v0.7
  356. 20.1 CADGenBench submission anonymous_v0-4_20261105-153344: v0.4
  357. 20.1 CADGenBench submission anonymous_v0-3_20261105-153341: v0.3
  358. 20.0 CADGenBench submission bruno-mutagent_mutagent-brepsmith-sonnet-5-agentic-harn_20260827-080517: mutagent-brepsmith — Sonnet-5 agentic harness (editing-only) r3
  359. 19.9 CADGenBench submission anon-170934_anon-170934_20260910-195151: anon_170934
  360. 19.8 CADGenBench submission anonymous_anonymous-agent_20260917-082500: Anonymous agent
  361. 19.5 CADGenBench submission toparo-8937_gen17-toparo-8937_20261023-010520: gen17-toparo-8937
  362. 19.5 CADGenBench submission anonymous_v0-1_20261105-153003: v0.1
  363. 19.4 CADGenBench submission vasere-1792_gen17-vasere-1792_20261021-222031: gen17-vasere-1792
  364. 19.2 CADGenBench submission indian-peafowl_india_20260718-185300: India
  365. 18.8 CADGenBench submission anonymous_anon-gen-1788819313-1f8489_20260907-221515: anon-gen-1788819313-1f8489
  366. 18.5 CADGenBench submission anon-201155_sweep-e_20260910-210303: sweep-e
  367. 18.4 CADGenBench submission james-dillard_gpt-5-nano-candidate-c-pi-harness-2026-0_20260828-001340: GPT-5 Nano Candidate C (Pi harness, 2026-08-27)
  368. 18.4 CADGenBench submission temape-4542_gen16-temape-4542_20261023-010547: gen16-temape-4542
  369. 18.3 GLM-4.6V
  370. 18.3 CADGenBench submission gikabe-3612_gen16-gikabe-3612_20261021-221910: gen16-gikabe-3612
  371. 18.3 CADGenBench submission cad-mcp-research_generation49-matched-evaluation-cell-248_20260824-080450: generation49 matched evaluation cell-2485f2e31202edef62dc
  372. 18.1 CADGenBench submission cad-mcp-research_baseline-protected-v0-7-11-all-generatio_20260824-183530: baseline-protected v0.7.11 all-generation CAD-MCP v0.7
  373. 18.0 CADGenBench submission origogk_origogk-sparse-suite-snapshot_20260926-142938: OrigoGK sparse suite snapshot
  374. 18.0 CADGenBench submission anonymous_run-5f161034-1787724840_20260826-061750: run-5f161034-1787724840
  375. 18.0 CADGenBench submission cad-mcp-research_baseline-protected-v0-7-11-all-generatio_20260824-182537: baseline-protected v0.7.11 all-generation Vanilla checkpoints
  376. 17.6 CADGenBench submission james-dillard_gpt-5-nano-candidate-j-pi-harness-2026-0_20260919-083944: GPT-5 Nano Candidate J (Pi harness, 2026-09-17)
  377. 17.6 CADGenBench submission giluze-5666_gen16-giluze-5666_20261022-184734: gen16-giluze-5666
  378. 17.4 CADGenBench submission cad-mcp-research_generation49-matched-evaluation-cell-8ee_20260824-081358: generation49 matched evaluation cell-8ee597dcef821bf18cf7
  379. 17.3 CADGenBench submission james-dillard_gpt-5-nano-candidate-e-pi-harness-2026-0_20260828-044843: GPT-5 Nano Candidate E (Pi harness, 2026-08-27)
  380. 17.2 CADGenBench submission anonymous_test-submission_20260819-015853: test-submission
  381. 17.1 CADGenBench submission origogk_origogk-contact-fix-adaptive-step_20260929-101124: OrigoGK contact-fix adaptive-step
  382. 17.1 CADGenBench submission arche_smith_20260709-222512: Smith
  383. 17.0 CADGenBench submission debumo-6710_gen16-debumo-6710_20261020-214856: gen16-debumo-6710
  384. 16.9 CADGenBench submission sibule-7638_gen16-sibule-7638_20261023-010458: gen16-sibule-7638
  385. 16.8 CADGenBench submission origogk_origogk-full-81-task-run-20260926_20260926-223823: OrigoGK full 81-task run 20260926
  386. 16.8 CADGenBench submission gen-harness-b_gen-harness-b_20260910-195259: gen-harness-b
  387. 16.8 CADGenBench submission sesado-1438_gen16-sesado-1438_20261021-153018: gen16-sesado-1438
  388. 16.8 Qwen3-VL-235B-A22B-Instruct
  389. 16.7 CADGenBench submission yeshenpy_qwen-ablation_20260903-115457: Qwen ablation
  390. 16.6 CADGenBench submission anonymous_o-a1_20261021-140503: O-A1
  391. 16.3 CADGenBench submission cad-mcp-blinded-study_cell-060ff6bdc2e19155fec8_20260821-084921: cell-060ff6bdc2e19155fec8
  392. 16.3 CADGenBench submission arche_smith_20260624-011205: Smith
  393. 16.3 CADGenBench submission baseline-v7_baseline-v7_20260910-195324: baseline-v7
  394. 16.2 CADGenBench submission cad-mcp-blinded-study_cell-04d75a55d41904fd073d_20260816-214010: cell-04d75a55d41904fd073d
  395. 16.1 CADGenBench submission yerin-choi_cad-mcp-paired-heldout-v1-vanilla-replic_20260814-143514: CAD-MCP paired heldout v1 vanilla replicate 3
  396. 16.1 CADGenBench submission cad-mcp-blinded-study_cell-08f852f7019f1b414b3a_20260821-085827: cell-08f852f7019f1b414b3a
  397. 16.0 CADGenBench submission experiment_experiment-partial-32-81-diagnostic_20260821-231550: Experiment - partial 32/81 diagnostic
  398. 15.8 CADGenBench submission james-dillard_gpt-5-nano-candidate-h-pi-harness-2026-0_20260901-101026: GPT-5 Nano Candidate H (Pi harness, 2026-08-31)
  399. 15.8 CADGenBench submission cad-mcp-blinded-study_cell-1f61f132aa5bd4b4be8c_20260821-090655: cell-1f61f132aa5bd4b4be8c
  400. 15.6 CADGenBench submission rigazu-5835_edit16-rigazu-5835_20261030-011458: edit16-rigazu-5835
  401. 15.6 CADGenBench submission yerin-choi_cad-mcp-paired-heldout-v1-cad-mcp-replic_20260814-143420: CAD-MCP paired heldout v1 cad_mcp replicate 2
  402. 15.4 CADGenBench submission local-user_codex-current-original-49-20261018-01_20261018-114008: codex-current-original-49-20261018-01
  403. 15.4 CADGenBench submission cad-mcp-blinded-study_cell-83efce1eb738ad54f712_20260821-091255: cell-83efce1eb738ad54f712
  404. 15.4 CADGenBench submission arche_smith_20260709-215857: Smith
  405. 15.3 CADGenBench submission cad-mcp-blinded-study_cell-92f624fa3400d7055063_20260816-220722: cell-92f624fa3400d7055063
  406. 15.3 CADGenBench submission yerin-choi_cad-mcp-paired-heldout-v1-vanilla-replic_20260814-143318: CAD-MCP paired heldout v1 vanilla replicate 2
  407. 15.3 CADGenBench submission ronado-1508_edit16-ronado-1508_20261024-154510: edit16-ronado-1508
  408. 15.2 CADGenBench submission goliki-7696_edit16-goliki-7696_20261024-154539: edit16-goliki-7696
  409. 15.1 CADGenBench submission cad-mcp-blinded-study_cell-f8302b92ab6b809510a9_20260821-092551: cell-f8302b92ab6b809510a9
  410. 15.0 CADGenBench submission huggingface_gpt-5-6-sol-hf-baseline-pipeline-test_20260807-094609: GPT-5.6 Sol HF Baseline (pipeline test)
  411. 14.9 CADGenBench submission fefona-2711_edit16-fefona-2711_20261030-011434: edit16-fefona-2711
  412. 14.9 CADGenBench submission cad-mcp-blinded-study_cell-c9bba894d207e6be92fd_20260816-221300: cell-c9bba894d207e6be92fd
  413. 14.8 CADGenBench submission arche_smith_20260709-215034: Smith
  414. 14.8 CADGenBench submission yerin-choi_cad-mcp-paired-heldout-v1-cad-mcp-replic_20260814-143202: CAD-MCP paired heldout v1 cad_mcp replicate 1
  415. 14.7 CADGenBench submission cad-mcp-blinded-study_cell-4603538f259e6df50d72_20260816-215447: cell-4603538f259e6df50d72
  416. 14.6 CADGenBench submission yerin-choi_cad-mcp-paired-heldout-v1-vanilla-replic_20260814-142911: CAD-MCP paired heldout v1 vanilla replicate 1
  417. 14.6 CADGenBench submission daanderson_fsmcp-opus-4-8-stl_20260616-122528: FSMCP+Opus 4.8 - STL
  418. 14.4 CADGenBench submission arche_smith_20260709-212542: Smith
  419. 14.3 CADGenBench submission cad-mcp-blinded-study_cell-85da63afedcb6c20f060_20260816-220149: cell-85da63afedcb6c20f060
  420. 14.2 CADGenBench submission yerin-choi_cad-mcp-paired-heldout-v1-cad-mcp-replic_20260814-143620: CAD-MCP paired heldout v1 cad_mcp replicate 3
  421. 14.0 CADGenBench submission anonymous_run-3283c228-1787609057_20260824-222220: run-3283c228-1787609057
  422. 14.0 CADGenBench submission anonymous_run-3283c228-1787609057_20260824-232333: run-3283c228-1787609057
  423. 13.9 CADGenBench submission cad-mcp-blinded-study_cell-329c6ab62a4397e86819_20260816-214811: cell-329c6ab62a4397e86819
  424. 13.7 CADGenBench submission cad-mcp-blinded-study_cell-d5fe8f58a164aa9aee2a_20260821-092007: cell-d5fe8f58a164aa9aee2a
  425. 13.5 CADGenBench submission anonymous_anon-edi-1788819332-ce4901_20260907-221535: anon-edi-1788819332-ce4901
  426. 13.5 CADGenBench submission yeshenpy_a-r2_20260902-081542: A-r2
  427. 13.4 CADGenBench submission anonymous_run-4934da30-1787675208_20260825-163254: run-4934da30-1787675208
  428. 13.4 CADGenBench submission anonymous_run-5f161034-1787686551_20260825-193825: run-5f161034-1787686551
  429. 12.5 CADGenBench submission anonymous_run-797978e8-1787636081_20260825-053639: run-797978e8-1787636081
  430. 12.4 CADGenBench submission anonymous_run-ca7da17d-1787680716_20260825-180307: run-ca7da17d-1787680716
  431. 12.4 CADGenBench submission anonymous_run-863e3c01-1788312265_20260902-012426: run-863e3c01-1788312265
  432. 12.4 CADGenBench submission james-dillard_gpt-5-nano-candidate-a-pi-harness-2026-0_20260827-100706: GPT-5 Nano Candidate A (Pi harness, 2026-08-26)
  433. 12.3 CADGenBench submission phi-linh_cad-gen-gpt-5-mini-v1_20260713-215232: cad-gen gpt-5-mini v1
  434. 12.3 CADGenBench submission phi-linh_cad-gen-gpt-5-mini-v1_20260713-215219: cad-gen gpt-5-mini v1
  435. 12.3 CADGenBench submission anonymous_anonymous-agent_20260916-133147: Anonymous agent
  436. 12.2 CADGenBench submission anonymous_run-46e66701-1787624064_20260825-040828: run-46e66701-1787624064
  437. 12.0 CADGenBench submission anonymous_run-8baebabe-1788313256_20260902-014057: run-8baebabe-1788313256
  438. 11.6 CADGenBench submission arche_smith_20260708-000637: Smith
  439. 11.5 CADGenBench submission arche_smith_20260708-062950: Smith
  440. 11.4 CADGenBench submission anonymous_anonymous-agent_20260916-183114: Anonymous agent
  441. 11.4 CADGenBench submission arche_smith_20260708-065352: Smith
  442. 11.4 CADGenBench submission arche_smith_20260623-230519: Smith
  443. 11.4 CADGenBench submission arche_smith_20260624-001648: Smith
  444. 10.9 CADGenBench submission james-dillard_gpt-5-nano-candidate-d-pi-harness-2026-0_20260828-025518: GPT-5 Nano Candidate D (Pi harness, 2026-08-27)
  445. 10.5 CADGenBench submission yitong42_codex-gpt-5-6-sol-high-15-sample_20260811-162034: Codex + gpt-5.6-sol high (15-sample)
  446. 10.5 CADGenBench submission origogk_origogk-1mm-full-input-diagnostic_20260929-052612: OrigoGK 1mm full-input diagnostic
  447. 10.1 CADGenBench submission cadse_brief-v7-fable-5-2-builder-effort-high-9_20261112-185357: brief v7, Fable 5.2 builder effort high, 9 fixtures (seed 20261112)
  448. 9.92 CADGenBench submission anonymous_anon-gen-1788761670-72e736_20260907-061431: anon-gen-1788761670-72e736
  449. 9.86 CADGenBench submission pave-cad_pave-cad-tool-assisted-no-skill-build123_20260712-165946: PAVE-CAD tool_assisted_no_skill_build123d.v2 (cadgenbench_langgraph_qwen37_plus_20260526)
  450. 9.83 CADGenBench submission daanderson_fs-mcp-opus-4-8-minimal-harness_20260615-131636: FS MCP - Opus 4.8 - Minimal Harness
  451. 9.72 CADGenBench submission cadse_review-arm-brief-v7-builds-after-blind-r_20261112-155250: Review arm: brief v7 builds after blind review and fix, nine fixtures
  452. 9.68 CADGenBench submission cadse_small-offset-r7x-effort-xhigh-solids-shi_20261112-111053: small offset r7x: effort xhigh solids shifted by 0.7 % of the diagonal (alignment test), 9 random fixtures (seed 20261112)
  453. 9.63 CADGenBench submission cadse_brief-v7-on-dyno-nine-fixtures-effort-ma_20261112-151818: Brief v7 on dyno: nine fixtures, effort max, one build per part
  454. 9.50 CADGenBench submission timeci-8199_gen8-timeci-8199_20261018-155944: gen8-timeci-8199
  455. 9.42 CADGenBench submission miles-bimrose_qwen3-vl-8b-build123d-finetune_20260611-212111: Qwen3-VL-8B build123d finetune
  456. 9.27 CADGenBench submission yitong42_pi-agent-gpt-5-6-sol-high-15-sample_20260811-164701: Pi Agent + gpt-5.6-sol high (15-sample)
  457. 9.26 CADGenBench submission cadse_effort-xhigh-r7x-full-brief-principles-h_20261112-095633: effort xhigh r7x: full brief + principles + hole rules v2, Opus builder, 9 random fixtures (seed 20261112)
  458. 8.97 CADGenBench submission cadse_guarded-offset-r5-round-5-solids-shifted_20261112-093438: guarded offset r5: round 5 solids shifted 1.5 % unless near-symmetric (alignment test), 9 random fixtures (seed 20261112)
  459. 8.97 CADGenBench submission cadse_small-offset-r5-round-5-solids-shifted-b_20261112-111149: small offset r5: round 5 solids shifted by 0.7 % of the diagonal (alignment test), 9 random fixtures (seed 20261112)
  460. 8.90 CADGenBench submission cadse_pose-rotx-r5-round-5-solids-turned-180-d_20261112-090958: pose rotx r5: round 5 solids turned 180 deg about x (alignment test), 9 random fixtures (seed 20261112)
  461. 8.84 CADGenBench submission pzfreo_build123d-mcp-0-3-85-dev0-gpt-6-astra-hi_20260905-060736: build123d-mcp-0.3.85.dev0-gpt-6-astra-high
  462. 8.79 CADGenBench submission james-dillard_gpt-5-nano-candidate-b-pi-harness-2026-0_20260827-101758: GPT-5 Nano Candidate B (Pi harness, 2026-08-26)
  463. 8.78 CADGenBench submission alexchunlin_claude-opus-5-5-blender-cadlib-drawing-t_20261027-223010: Claude Opus 5.5 + Blender/cadlib + drawing tools (OCR, measure, holes, overlay), faceted STEP (10-sample)
  464. 8.76 CADGenBench submission cadse_small-offset-lean3-hole-rules-v2-lean-so_20261112-111231: small offset lean3: hole rules v2 lean solids shifted by 0.7 % of the diagonal (alignment test), 9 random fixtures (seed 20261112)
  465. 8.69 CADGenBench submission cadse_small-offset-r6-round-6-solids-shifted-b_20261112-092806: small offset r6: round 6 solids shifted by 0.7 % of the diagonal (alignment test), 9 random fixtures (seed 20261112)
  466. 8.68 CADGenBench submission cadse_economy-mode-off-buildbox-principles-v4-_20261112-071308: economy mode off: buildbox principles v4 + scoring-aware brief + zoom, Opus builder, 9 random fixtures (seed 20261112)
  467. 8.66 CADGenBench submission cadse_offset-lean3-hole-rules-v2-lean-solids-s_20261112-090323: offset lean3: hole rules v2 lean solids shifted by 1.5 % of the diagonal (alignment test), 9 random fixtures (seed 20261112)
  468. 8.63 CADGenBench submission origogk_origogk-generation-housing-diagnostic-20_20260926-060753: OrigoGK generation housing diagnostic 20260926
  469. 8.63 CADGenBench submission alexchunlin_claude-opus-5-5-plain-build123d-10-sampl_20261027-144651: Claude Opus 5.5 + plain build123d (10-sample pilot, comparison arm)
  470. 8.63 CADGenBench submission cadse_pose-rotz-r5-round-5-solids-turned-180-d_20261112-090903: pose rotz r5: round 5 solids turned 180 deg about z (alignment test), 9 random fixtures (seed 20261112)
  471. 8.60 CADGenBench submission borisyich_freecad-mcp-v1-37-gpt-5-6-high-some_20260817-090235: freecad-mcp-v1.37-gpt-5.6-high-some
  472. 8.60 CADGenBench submission cadse_offset-r6-round-6-solids-shifted-by-1-5-_20261112-090242: offset r6: round 6 solids shifted by 1.5 % of the diagonal (alignment test), 9 random fixtures (seed 20261112)
  473. 8.60 CADGenBench submission cadse_pose-roty-r5-round-5-solids-turned-180-d_20261112-091042: pose roty r5: round 5 solids turned 180 deg about y (alignment test), 9 random fixtures (seed 20261112)
  474. 8.36 CADGenBench submission cadse_round-6-full-brief-principles-hole-rules_20261112-083429: round 6: full brief + principles + hole rules v2, Opus builder, 9 random fixtures (seed 20261112)
  475. 8.34 CADGenBench submission pzfreo_opus5-xhigh-official-baseline-prompt-nom_20260809-222310: opus5-xhigh-official-baseline-prompt-nomcp-partial11-r1
  476. 8.31 CADGenBench submission cadse_hole-rules-v2-lean-prompt-zoom-opus-buil_20261112-080413: hole rules v2: lean prompt + zoom, Opus builder, 9 random fixtures (seed 20261112)
  477. 8.18 CADGenBench submission cadse_passage-and-hole-rules-lean-prompt-zoom-_20261112-072345: passage and hole rules: lean prompt + zoom, Opus builder, 9 random fixtures (seed 20261112)
  478. 7.97 CADGenBench submission cadse_repeat-r5b-full-brief-principles-v4-unch_20261112-102013: repeat r5b: full brief + principles v4, unchanged repeat of round 5, Opus builder, 9 random fixtures (seed 20261112)
  479. 7.94 CADGenBench submission alexchunlin_claude-opus-5-5-headless-blender-cadlib-_20261027-150637: Claude Opus 5.5 + headless Blender/cadlib, faceted STEP (10-sample pilot)
  480. 7.87 CADGenBench submission alexchunlin_claude-opus-5-5-blender-cadlib-faceted-s_20261027-215115: Claude Opus 5.5 + Blender/cadlib, faceted STEP (10-sample repeat, no drawing tools)
  481. 7.61 CADGenBench submission cadse_repeat-2-lean-prompt-no-principles-zoom-_20261112-071803: repeat 2: lean prompt (no principles) + zoom, Opus builder, 9 random fixtures (seed 20261112)
  482. 7.56 CADGenBench submission petrichor_petrichor_20260909-071845: petrichor
  483. 7.51 CADGenBench submission cadse_lean-prompt-no-principles-zoom-opus-buil_20261112-055409: lean prompt (no principles) + zoom, Opus builder, 9 random fixtures (seed 20261112)
  484. 7.30 CADGenBench submission min-liu_chamfer-t1-edit-smoke15_20260709-013607: chamfer-t1-edit-smoke15
  485. 7.06 CADGenBench submission origogk_origogk-analytic-edits-diagnostic-202609_20260926-044655: OrigoGK analytic edits diagnostic 20260926
  486. 6.79 CADGenBench submission cadse_sheet-notes-r1-full-brief-principles-bui_20261112-111817: sheet notes r1: full brief + principles + build123d sheet-metal notes, 7 sheet-metal parts only, Opus builder (seed 20261112)
  487. 6.73 CADGenBench submission pzfreo_gpt-5-5-b123d-mcp-0-3-59-xhigh-smoke10-p_20260701-131749: gpt-5.5-b123d-mcp-0.3.59-xhigh-SMOKE10-P1
  488. 6.66 CADGenBench submission anon-181240_sweep-c2_20260910-202002: sweep-c2
  489. 6.63 CADGenBench submission cadse_buildbox-principles-v3-compare-loop-opus_20261112-040654: buildbox principles v3 + compare loop, Opus builder, 9 random fixtures (seed 20261112)
  490. 6.51 CADGenBench submission pzfreo_build123d-mcp-0-3-90-gemini-4-argon-high_20261021-205929: build123d-mcp-0.3.90-gemini-4-argon-high
  491. 6.43 CADGenBench submission cadse_buildbox-principles-v4-scoring-aware-bri_20261112-051241: buildbox principles v4 + scoring-aware brief + zoom, Opus builder, 9 random fixtures (seed 20261112)
  492. 6.35 CADGenBench submission reify_reify-sol-low-asi-202-209-paired-01_20261021-220527: reify-sol-low-asi-202-209-paired-01
  493. 6.34 CADGenBench submission cadse_hand-edited-diagnostic-probes-on-3-fixtu_20261112-061555: hand-edited diagnostic probes on 3 fixtures (single change each), other 6 = earlier run r3
  494. 6.25 CADGenBench submission cadse_buildbox-principles-v4-drawing-rules-com_20261112-043202: buildbox principles v4 (drawing rules) + compare loop, Opus builder, 9 random fixtures (seed 20261112)
  495. 6.14 CADGenBench submission cadse_buildbox-principles-opus-builder-9-rando_20261112-033752: buildbox principles + Opus builder, 9 random fixtures (seed 20261112)
  496. 6.09 CADGenBench submission pzfreo_build123d-mcp-0-3-83-fable-5-1-high_20260902-121723: build123d-mcp-0.3.83-fable-5.1-high
  497. 6.08 CADGenBench submission yitong42_matched-baseline-codex-gpt-5-6-sol-high-_20260906-170553: Matched baseline + Codex gpt-5.6-sol high (10-case)
  498. 6.04 CADGenBench submission lolopu-8948_edit8-lolopu-8948_20261030-011549: edit8-lolopu-8948
  499. 5.95 CADGenBench submission local-user_t047-inspect-feedback-six-20261029_20261029-155032: t047-inspect-feedback-six-20261029
  500. 5.91 CADGenBench submission origogk_origogk-sparse-dual-full-input-diagnosti_20260928-160948: OrigoGK sparse-dual full-input diagnostic
  501. 5.90 CADGenBench submission reify_reify-sol-low-naked-202-209-paired-01_20261021-220143: reify-sol-low-naked-202-209-paired-01
  502. 5.83 CADGenBench submission pzfreo_pzfreo_20260902-062348: pzfreo
  503. 5.82 CADGenBench submission yitong42_m2d-first-codex-gpt-5-6-sol-high-10-case_20260906-170530: M2D-first + Codex gpt-5.6-sol high (10-case)
  504. 5.82 CADGenBench submission local-user_t047-autonomous-feedback-six-20261030_20261030-010719: t047-autonomous-feedback-six-20261030
  505. 5.81 CADGenBench submission pzfreo_gpt55-v0368-smoke10_20260705-172407: gpt55-v0368-smoke10
  506. 5.75 CADGenBench submission pzfreo_gpt-5-5-b123d-mcp-0-3-59-xhigh-smoke10-n_20260627-171359: gpt-5.5-b123d-mcp-0.3.59-xhigh-SMOKE10-newprompt
  507. 5.70 CADGenBench submission reify_reify-deepseek-low-asi-217-238-01_20261023-070657: reify-deepseek-low-asi-217-238-01
  508. 5.65 CADGenBench submission cad-study_baseline-no-planning_20261007-140142: baseline-no_planning
  509. 5.64 CADGenBench submission anonymous_anon-gen-1788670318-98a7_20260906-045201: anon-gen-1788670318-98a7
  510. 5.61 CADGenBench submission anonymous_anon-gen-1788746242-74b911_20260907-015723: anon-gen-1788746242-74b911
  511. 5.48 CADGenBench submission anonymous_anon-gen-1788680583-e9d0_20260906-074305: anon-gen-1788680583-e9d0
  512. 5.45 CADGenBench submission anonymous_anon-gen-1788717334-a056_20260906-175535: anon-gen-1788717334-a056
  513. 5.28 CADGenBench submission pzfreo_agy-gemini37-flash-high-plan-mcp0383-smo_20260901-190641: agy-gemini37-flash-high-plan-mcp0383-smoke6
  514. 5.24 CADGenBench submission pzfreo_gpt55-pr40-pr403-smoke10_20260708-215753: gpt55-pr40-pr403-smoke10
  515. 5.19 CADGenBench submission local-user_t047-tool021-tx-a-20261029_20261029-060246: t047-tool021-tx-a-20261029
  516. 5.03 CADGenBench submission cad-study_baseline-graph-cad-planning_20261007-230611: baseline-graph_cad_planning
  517. 4.95 CADGenBench submission tamarind_tamarind_20260909-152727: tamarind
  518. 4.89 CADGenBench submission anonymous_anon-edi-1788761677-0e4b7e_20260907-061438: anon-edi-1788761677-0e4b7e
  519. 4.87 CADGenBench submission origogk_origogk-bounded-dual-full-input-diagnost_20260928-141343: OrigoGK bounded-dual full-input diagnostic
  520. 4.81 CADGenBench submission cad-study_baseline-cadcoder-planning_20261007-193721: baseline-cadcoder_planning
  521. 4.68 CADGenBench submission pzfreo_pzfreo-gpt55-v0375-smoke10-mcp_20260709-104821: pzfreo_gpt55-v0375-smoke10-mcp
  522. 4.66 CADGenBench submission cad-study_baseline-general-coding-plan_20261007-174344: baseline-general_coding-plan
  523. 4.62 CADGenBench submission local-user_t047-r3-b-r01-20261027_20261027-081850: t047-r3-b-r01-20261027
  524. 4.61 CADGenBench submission cad-study_baseline-no-plan-rerun_20261008-045844: baseline_no_plan_rerun
  525. 4.59 CADGenBench submission reify_reify-deepseek-low-naked-217-238-paralle_20261023-030248: reify-deepseek-low-naked-217-238-parallel-01
  526. 4.57 CADGenBench submission pzfreo_fable5-v0360-med-eff-smoke5_20260702-042807: fable5-v0360-med-eff-smoke5
  527. 4.55 CADGenBench submission anonymous_anon-gen-1787740768-01a0_20260826-103929: anon-gen-1787740768-01a0
  528. 4.55 CADGenBench submission yitong42_native-gpt-6-astra-ultra-baseline-4-case_20260917-050440: Native GPT-6 Astra Ultra baseline 4-case 20260916-235800
  529. 4.48 CADGenBench submission anonymous_anon-gen-1788675770-a7c0_20260906-062252: anon-gen-1788675770-a7c0
  530. 4.46 CADGenBench submission pzfreo_build123d-mcp-0-3-84-dev0-gemini-3-8-fla_20260903-113023: build123d-mcp-0.3.84.dev0-gemini-3.8-flash-high-recognition-editing6-r2
  531. 4.41 CADGenBench submission yitong42_native-gpt-6-astra-ultra-svg-first-4-cas_20260917-050647: Native GPT-6 Astra Ultra svg-first 4-case 20260916-235800
  532. 4.37 CADGenBench submission reify_reify-sol-low-asi-217-238-parallel-01_20261023-030814: reify-sol-low-asi-217-238-parallel-01
  533. 4.35 CADGenBench submission cajuce-1755_gen4-cajuce-1755_20261017-164050: gen4-cajuce-1755
  534. 4.34 CADGenBench submission miles-bimrose_qwen3-vl-2b-build123d-finetune_20260609-204140: Qwen3-VL-2B build123d finetune
  535. 4.30 CADGenBench submission cad-study_baseline-no-planning-corrected_20261010-041632: baseline-no_planning_corrected
  536. 4.29 CADGenBench submission anonymous_anon-gen-1787964784-d19c_20260829-005305: anon-gen-1787964784-d19c
  537. 4.29 CADGenBench submission anonymous_anon-gen-1787967441-5839_20260829-013722: anon-gen-1787967441-5839
  538. 4.27 CADGenBench submission pzfreo_gpt-5-5-b123d-mcp-0-3-59-xhigh-resmoke7-_20260627-192314: gpt-5.5-b123d-mcp-0.3.59-xhigh-RESMOKE7-fixed
  539. 4.26 CADGenBench submission reify_reify-sol-low-asi-211-215-config-01_20261022-062053: reify-sol-low-asi-211-215-config-01
  540. 4.13 CADGenBench submission local-user_t047-full-mid-feedback-six-20261030_20261029-192823: t047-full-mid-feedback-six-20261030
  541. 4.03 CADGenBench submission pidebe-5079_gen4-pidebe-5079-r2_20261016-172912: gen4-pidebe-5079-r2
  542. 3.94 CADGenBench submission anonymous_anon-gen-1788548779-3c7e_20260904-190620: anon-gen-1788548779-3c7e
  543. 3.87 CADGenBench submission local-user_t047-0770-b-dev4-20261027_20261026-190236: t047-0770-B-dev4-20261027
  544. 3.84 CADGenBench submission anonymous_anon-gen-1789088535-1624c8_20260911-010919: anon-gen-1789088535-1624c8
  545. 3.80 CADGenBench submission local-user_t047-0771-p-dev4-20261027_20261026-190417: t047-0771-P-dev4-20261027
  546. 3.77 CADGenBench submission origogk_origogk-native-triangle-kernel-diagnosti_20260928-114945: OrigoGK native-triangle kernel diagnostic
  547. 3.72 CADGenBench submission local-user_t047-0771-p2-dev4-20261027_20261027-034922: t047-0771-P2-dev4-20261027
  548. 3.69 CADGenBench submission cadse_qwen3-8-flash-next-local-4-bit-thinking-_20261112-071939: Qwen3.8-Flash-Next (local, 4 bit, thinking on): lean prompt + API idioms + check loop, 9 random fixtures (seed 20261112)
  549. 3.60 CADGenBench submission cadse_qwen3-8-flash-next-local-4-bit-thinking-_20261112-074554: Qwen3.8-Flash-Next (local, 4 bit, thinking on): principles text + API idioms + check loop, 9 random fixtures (seed 20261112)
  550. 3.55 CADGenBench submission w1ne_kernelcad-probe-edit-v4-20261020_20261020-013517: kernelcad-probe-edit-v4-20261020
  551. 3.52 CADGenBench submission pzfreo_opus5-xhigh-mcp-source-backed-sample6-r1_20260811-100624: opus5-xhigh-mcp-source-backed-sample6-r1
  552. 3.52 CADGenBench submission origogk_origogk-surface-bounds-same12-diagnostic_20260928-122509: OrigoGK surface-bounds same12 diagnostic
  553. 3.50 CADGenBench submission cadse_flash-next-read-sheet-notes-read-then-co_20261112-135102: Flash-Next read + sheet notes: read-then-compare with sheet-metal notes on 108 and 114, 9 random fixtures (seed 20261112)
  554. 3.48 CADGenBench submission anonymous_anon-edit-1788032760-be22_20260829-194601: anon-edit-1788032760-be22
  555. 3.43 CADGenBench submission local-user_t047-r3-p2-r01-20261027_20261027-082316: t047-r3-p2-r01-20261027
  556. 3.43 CADGenBench submission cadse_flash-next-lean-r2-qwen3-8-flash-next-on_20261112-135027: Flash-Next lean r2: Qwen3.8-Flash-Next on Brev, thinking on, 12 rounds, 9 random fixtures (seed 20261112)
  557. 3.41 CADGenBench submission pzfreo_opus5-xhigh-minimal-mcp-cross-sections-s_20260813-051907: opus5-xhigh-minimal-mcp-cross-sections-sample6-r4
  558. 3.35 CADGenBench submission cadse_flash-next-read-then-compare-qwen3-8-fla_20261112-134952: Flash-Next read-then-compare: Qwen3.8-Flash-Next on Brev, reads dimensions first and keeps the best-agreeing build, 9 random fixtures (seed 20261112)
  559. 3.30 CADGenBench submission pzfreo_pzfreo-opus5-xhigh-mcp-fidelity-workflow_20260812-191538: pzfreo-opus5-xhigh-mcp-fidelity-workflow-fe01ca8-sample6-r1
  560. 3.30 CADGenBench submission local-user_t047-end-review-a-three-20261030_20261030-043124: t047-end-review-a-three-20261030
  561. 3.29 CADGenBench submission anonymous_anon-gen-1788389662-455b_20260902-225424: anon-gen-1788389662-455b
  562. 3.29 CADGenBench submission anonymous_anon-gen-1788407486-cf7b_20260903-035127: anon-gen-1788407486-cf7b
  563. 3.25 CADGenBench submission anonymous_run-y_20261112-115942: Run Y
  564. 3.24 CADGenBench submission anonymous_anon-gen-1788030000-4639_20260829-190002: anon-gen-1788030000-4639
  565. 3.24 CADGenBench submission anonymous_ab_20261112-143821: AB
  566. 3.19 CADGenBench submission yitong42_svga-g-r1-gpt6-svg-gpt56-cad-840e3511902_20260928-042929: SVGA G-r1 GPT6 SVG GPT56 CAD 840e35119023
  567. 3.19 CADGenBench submission local-user_t051-r012-c-frozen-followup-20261103_20261103-144030: t051-r012-c-frozen-followup-20261103
  568. 3.19 CADGenBench submission anonymous_aa_20261112-135052: AA
  569. 3.14 CADGenBench submission anonymous_anon-gen-1788486936-fd25_20260904-015537: anon-gen-1788486936-fd25
  570. 3.14 CADGenBench submission local-user_t047-tool021-tx-b-20261029_20261029-060423: t047-tool021-tx-b-20261029
  571. 3.12 CADGenBench submission anonymous_anon-gen-1788549253-6668_20260904-191414: anon-gen-1788549253-6668
  572. 3.12 CADGenBench submission anonymous_anon-gen-1788549393-ab57_20260904-191634: anon-gen-1788549393-ab57
  573. 3.10 CADGenBench submission local-user_t051-r010-b2-c_20261102-191249: t051-r010-b2-c
  574. 3.09 CADGenBench submission yitong42_gpt-6-astra-ultra-svg-gpt-5-6-sol-high-c_20260907-173941: GPT-6 Astra Ultra SVG + GPT-5.6-sol high CAD (4-case)
  575. 3.06 CADGenBench submission min-liu_chamfer-t2-gen-smoke9_20260709-013720: chamfer-t2-gen-smoke9
  576. 3.06 CADGenBench submission pzfreo_opus5-xhigh-mcp-conditional-source-sampl_20260811-160112: opus5-xhigh-mcp-conditional-source-sample6-r1
  577. 3.03 CADGenBench submission local-user_t051-r004-c_20261102-022312: t051-r004-c
  578. 3.03 CADGenBench submission local-user_t051-r004-c-infra-retry1_20261102-040853: t051-r004-c-infra-retry1
  579. 2.98 CADGenBench submission min-liu_cad-agent-probe-fusion-360-mcp-x-claude-_20260704-232309: cad-agent probe (Fusion 360 MCP x Claude Opus, fixtures 101-108)
  580. 2.96 CADGenBench submission yitong42_svga-g-r2-gpt6-svg-gpt56-cad-840e3511902_20260928-042939: SVGA G-r2 GPT6 SVG GPT56 CAD 840e35119023
  581. 2.95 CADGenBench submission cad-mcp-research_inspection-first-comparison-cell-0746582_20260824-054050: inspection-first comparison cell-074658225db50681b737
  582. 2.94 CADGenBench submission anonymous_run-x_20261112-115818: Run X
  583. 2.93 CADGenBench submission local-user_t051-r010-b2-b_20261102-194032: t051-r010-b2-b
  584. 2.92 CADGenBench submission local-user_t047-772-fresh-three-a-20261031_20261030-174933: t047-772-fresh-three-a-20261031
  585. 2.90 CADGenBench submission local-user_t051-r005-c_20261102-061259: t051-r005-c
  586. 2.90 CADGenBench submission local-user_t051-r010-b1-c_20261102-184255: t051-r010-b1-c
  587. 2.88 CADGenBench submission yitong42_svgq-a-r1-gpt56-high-618c9855edcd_20260927-191017: SVGQ A-r1 GPT56 high 618c9855edcd
  588. 2.86 CADGenBench submission local-user_t051-r010-b1-a_20261102-185031: t051-r010-b1-a
  589. 2.86 CADGenBench submission local-user_t051-r010-b2-a_20261102-192434: t051-r010-b2-a
  590. 2.86 CADGenBench submission anonymous_run-z_20261112-125840: Run Z
  591. 2.85 CADGenBench submission cad-mcp-research_inspection-first-comparison-cell-4c0ea99_20260824-055326: inspection-first comparison cell-4c0ea99f1d39970c13cd
  592. 2.83 CADGenBench submission local-user_t047-cvd1-t-20261028_20261028-094744: t047-cvd1-t-20261028
  593. 2.81 CADGenBench submission cad-mcp-research_inspection-first-comparison-cell-630b5e0_20260824-055912: inspection-first comparison cell-630b5e09508b67f40702
  594. 2.80 CADGenBench submission cad-mcp-research_inspection-first-comparison-cell-bb69143_20260824-061044: inspection-first comparison cell-bb691437fd2c19f879ed
  595. 2.79 CADGenBench submission local-user_t051-r010-b1-ab_20261102-190514: t051-r010-b1-ab
  596. 2.77 CADGenBench submission local-user_t047-cvd1-c-20261028_20261028-094122: t047-cvd1-c-20261028
  597. 2.76 CADGenBench submission pzfreo_fable5-v0360-xhigh-smoke3_20260701-221618: fable5-v0360-xhigh-SMOKE3
  598. 2.76 CADGenBench submission lehuili_gpt5-6-atomic-reflect-2d_20260909-042736: gpt5.6-atomic-reflect-2D
  599. 2.74 CADGenBench submission cad-mcp-research_inspection-first-development-cell-02cf3d_20260823-002431: inspection-first development cell-02cf3d0c30148c2ed1a1
  600. 2.71 CADGenBench submission yitong42_matched-baseline-codex-gpt-5-6-sol-high-_20260907-092712: Matched baseline + Codex gpt-5.6-sol high (semantic-v1, 4-case)
  601. 2.71 CADGenBench submission yitong42_svgq-d-r2-gpt56-high-618c9855edcd_20260927-191631: SVGQ D-r2 GPT56 high 618c9855edcd
  602. 2.66 CADGenBench submission anonymous_anon-gen-1787960079-6878_20260828-233440: anon-gen-1787960079-6878
  603. 2.66 CADGenBench submission anonymous_anon-gen-1787960533-2534_20260828-234214: anon-gen-1787960533-2534
  604. 2.65 CADGenBench submission cad-mcp-research_inspection-first-development-cell-a60fbd_20260823-014644: inspection-first development cell-a60fbdf6db6c69ed6e10
  605. 2.63 CADGenBench submission yitong42_svgq-c-r1-gpt56-high-618c9855edcd_20260927-191400: SVGQ C-r1 GPT56 high 618c9855edcd
  606. 2.62 CADGenBench submission reify_reify-deepseek-low-naked-211-215-config-_20261022-061630: reify-deepseek-low-naked-211-215-config-01
  607. 2.61 CADGenBench submission anon-190312_sweep-d3_20260910-205325: sweep-d3
  608. 2.61 CADGenBench submission local-user_t051-r007-t_20261102-085108: t051-r007-t
  609. 2.60 CADGenBench submission local-user_t051-r006-t_20261102-080915: t051-r006-t
  610. 2.59 CADGenBench submission yitong42_m2d-first-codex-gpt-5-6-sol-high-semanti_20260907-093502: M2D-first + Codex gpt-5.6-sol high (semantic-v1, 4-case)
  611. 2.58 CADGenBench submission local-user_t051-r008-t_20261102-094036: t051-r008-t
  612. 2.57 CADGenBench submission yitong42_oldprompt-paired-baseline-gpt-5-6-sol-hi_20260914-152659: OldPrompt paired baseline GPT-5.6-sol high 4-case 20260914-191500
  613. 2.55 CADGenBench submission cad-mcp-research_inspection-first-development-cell-0af180_20260823-003654: inspection-first development cell-0af180ba59a5f3524569
  614. 2.55 CADGenBench submission yitong42_metric-m-r1-gpt56-metric-first-svg-cad-e_20260929-090822: METRIC M-r1 GPT56 metric-first SVG CAD ef73db60fade
  615. 2.53 CADGenBench submission cad-mcp-research_inspection-first-development-cell-141a78_20260823-004305: inspection-first development cell-141a781f828c31cd9c2a
  616. 2.53 CADGenBench submission yitong42_oldprompt-paired-svg-first-gpt-5-6-sol-h_20260914-152659: OldPrompt paired svg-first GPT-5.6-sol high 4-case 20260914-191500
  617. 2.52 CADGenBench submission pzfreo_gpt55-v0364-xhigh-unstepped-retest_20260704-065437: gpt55-v0364-xhigh-unstepped-retest
  618. 2.52 CADGenBench submission local-user_t051-r010-b2-ab_20261102-194913: t051-r010-b2-ab
  619. 2.51 CADGenBench submission cad-mcp-research_inspection-first-development-cell-89a36d_20260823-013213: inspection-first development cell-89a36dbcaa2ca924fba8
  620. 2.51 CADGenBench submission yitong42_svgq-b-r1-gpt56-high-618c9855edcd_20260927-191216: SVGQ B-r1 GPT56 high 618c9855edcd
  621. 2.50 CADGenBench submission cad-mcp-research_inspection-first-development-cell-76a8b5_20260823-011808: inspection-first development cell-76a8b51ed947e4d1e963
  622. 2.49 CADGenBench submission yitong42_paired-baseline-gpt-5-6-sol-high-4-case-_20260914-100552: Paired baseline GPT-5.6-sol high 4-case 20260914-154500
  623. 2.48 CADGenBench submission local-user_t047-0773-feedback-a-20261101_20261101-030942: t047-0773-feedback-a-20261101
  624. 2.47 CADGenBench submission yitong42_svgq-b-r2-gpt56-high-618c9855edcd_20260927-191308: SVGQ B-r2 GPT56 high 618c9855edcd
  625. 2.47 CADGenBench submission yitong42_svgq-c-r2-gpt56-high-618c9855edcd_20260927-191451: SVGQ C-r2 GPT56 high 618c9855edcd
  626. 2.45 CADGenBench submission pzfreo_gpt55-v0373-smoke5_20260708-102200: gpt55-v0373-smoke5
  627. 2.45 CADGenBench submission cad-mcp-research_inspection-first-development-cell-fbc1fc_20260823-015341: inspection-first development cell-fbc1fc0ce6dc251d5efc
  628. 2.45 CADGenBench submission yitong42_paired-svg-first-gpt-5-6-sol-high-4-case_20260914-100759: Paired svg-first GPT-5.6-sol high 4-case 20260914-154500
  629. 2.45 CADGenBench submission local-user_gemini38-0773-baseline-20261103-fixturef_20261103-031745: gemini38-0773-baseline-20261103-fixturefix1
  630. 2.44 CADGenBench submission cad-mcp-research_inspection-first-development-cell-067743_20260823-003051: inspection-first development cell-0677434281d885366a2f
  631. 2.43 CADGenBench submission cad-mcp-research_inspection-first-development-cell-fbe5f2_20260823-015910: inspection-first development cell-fbe5f2475be209c783a8
  632. 2.43 CADGenBench submission yitong42_metric-m-r2-gpt56-metric-first-svg-cad-e_20260929-090912: METRIC M-r2 GPT56 metric-first SVG CAD ef73db60fade
  633. 2.41 CADGenBench submission niming_a-research_20261002-075325: a_research
  634. 2.41 CADGenBench submission local-user_t051-r004-t_20261102-022533: t051-r004-t
  635. 2.41 CADGenBench submission local-user_t051-r004-t-infra-retry1_20261102-041126: t051-r004-t-infra-retry1
  636. 2.40 CADGenBench submission one-research_gpt-5-6-sol-v9-step-r3-101-102-103-128_20260913-135427: GPT-5.6-sol-v9-step-r3-101-102-103-128
  637. 2.39 CADGenBench submission cad-mcp-research_inspection-first-development-cell-6415c0_20260823-010753: inspection-first development cell-6415c0063e381291cecd
  638. 2.39 CADGenBench submission yitong42_direct-svg-first-codex-gpt-5-6-sol-high-_20260907-134035: Direct SVG-first + Codex gpt-5.6-sol high (svg-v2, 4-case)
  639. 2.39 CADGenBench submission local-user_t051-r001-d02_20261101-080615: t051-r001-d02
  640. 2.38 CADGenBench submission wolf_pi-agent-4cases-step_20260908-083822: pi-agent-4cases-step
  641. 2.38 CADGenBench submission local-user_t051-r006-c_20261102-080053: t051-r006-c
  642. 2.36 CADGenBench submission yitong42_svgq-a-r2-gpt56-high-618c9855edcd_20260927-191126: SVGQ A-r2 GPT56 high 618c9855edcd
  643. 2.36 CADGenBench submission local-user_t047-d1-a-r02-20261027_20261027-162331: t047-d1-a-r02-20261027
  644. 2.35 CADGenBench submission gkgyc233_a-test-of-one-sample-on-gpt-6-astra_20260912-103520: A test of one sample on GPT 6 Astra
  645. 2.34 CADGenBench submission local-user_t047-d1-b-r01-20261027_20261027-163207: t047-d1-b-r01-20261027
  646. 2.34 CADGenBench submission local-user_t047-d1-b-r02-20261027_20261027-162745: t047-d1-b-r02-20261027
  647. 2.31 CADGenBench submission cad-mcp-research_inspection-first-development-cell-7eb40f_20260823-012428: inspection-first development cell-7eb40ff4e913fca57016
  648. 2.31 CADGenBench submission local-user_t051-r001-c_20261101-080327: t051-r001-c
  649. 2.31 CADGenBench submission local-user_t051-r001-d03_20261101-080656: t051-r001-d03
  650. 2.30 CADGenBench submission yitong42_autonomous-svg-codex-gpt-5-6-sol-high-ca_20260908-062724: Autonomous SVG + Codex GPT-5.6-sol high CAD (4-case)
  651. 2.29 CADGenBench submission marzipan_marzipan_20260910-003143: marzipan
  652. 2.27 CADGenBench submission w1ne_kernelcad-probe-gen-20261019_20261019-184630: kernelcad-probe-gen-20261019
  653. 2.26 CADGenBench submission cad-mcp-research_inspection-first-development-cell-00372f_20260823-001706: inspection-first development cell-00372fd9856d4285f61b
  654. 2.26 CADGenBench submission yitong42_svgq-d-r1-gpt56-high-618c9855edcd_20260927-191541: SVGQ D-r1 GPT56 high 618c9855edcd
  655. 2.22 CADGenBench submission cad-mcp-research_inspection-first-development-cell-94b7ca_20260823-014156: inspection-first development cell-94b7ca74fcea622f3cac
  656. 2.21 CADGenBench submission arisa_gpt-5-6-sol-step-wise-strategy-v1-r2-101_20260914-114547: GPT-5.6-sol-step-wise-strategy-v1-r2-101-102-103-128
  657. 2.20 CADGenBench submission local-user_t051-r001-d01_20261101-080528: t051-r001-d01
  658. 2.19 CADGenBench submission cad-mcp-research_inspection-first-development-cell-1e4c04_20260823-005013: inspection-first development cell-1e4c046ffffb40877352
  659. 2.19 CADGenBench submission cad-mcp-research_inspection-first-development-cell-357d7d_20260823-005637: inspection-first development cell-357d7d06dcbee1ede716
  660. 2.19 CADGenBench submission local-user_t047-772-feedback-repair-two-20261030_20261030-160122: t047-772-feedback-repair-two-20261030
  661. 2.17 CADGenBench submission local-user_t047-0773-feedback-b-20261101_20261101-034711: t047-0773-feedback-b-20261101
  662. 2.16 CADGenBench submission anonymous_anon-gen-1787959342-3f06_20260828-232223: anon-gen-1787959342-3f06
  663. 2.16 CADGenBench submission yitong42_m2d-first-codex-gpt-5-6-sol-high-4-case-_20260906-070144: M2D-first + Codex gpt-5.6-sol high (4-case, 20260906)
  664. 2.15 CADGenBench submission local-user_t051-r009-t_20261102-131444: t051-r009-t
  665. 2.14 CADGenBench submission local-user_t051-r007-c_20261102-084233: t051-r007-c
  666. 2.13 CADGenBench submission lehuili_gpt-5-6-sol-self-reflect-2d-inspect-4-ca_20260822-071528: GPT-5.6 Sol Self Reflect + 2D Inspect (4-case)
  667. 2.13 CADGenBench submission cad-edit_edit-5-sample-run_20261011-125812: edit-5-sample-run
  668. 2.13 CADGenBench submission local-user_t051-r005-t_20261102-063046: t051-r005-t
  669. 2.13 CADGenBench submission local-user_t051-r009-c_20261102-130716: t051-r009-c
  670. 2.11 CADGenBench submission anonymous_ac_20261112-154838: AC
  671. 2.11 CADGenBench submission anonymous_ac_20261112-160639: AC
  672. 2.06 CADGenBench submission cad-mcp-research_inspection-first-comparison-cell-90ac68c_20260824-060431: inspection-first comparison cell-90ac68cb965dd8f90995
  673. 2.04 CADGenBench submission local-user_t047-tool021-diag-t-r1-20261029_20261029-024855: t047-tool021-diag-t-r1-20261029
  674. 2.03 CADGenBench submission lehuili_gpt-5-6-sol-self-reflect-second-pass-4-c_20260821-152311: GPT-5.6 Sol Self Reflect Second Pass (4-case)
  675. 2.03 CADGenBench submission arisa_gpt-5-6-sol-step-wise-strategy-v1-r1-101_20260914-114510: GPT-5.6-sol-step-wise-strategy-v1-r1-101-102-103-128
  676. 2.02 CADGenBench submission local-user_t047-tool021-diag-c-r1-20261029_20261029-024716: t047-tool021-diag-c-r1-20261029
  677. 2.02 CADGenBench submission local-user_t047-772-fresh-three-b-20261031_20261030-175017: t047-772-fresh-three-b-20261031
  678. 2.01 CADGenBench submission lehuili_gpt-5-6-sol-self-reflect-2d-inspect-same_20260822-083539: GPT-5.6 Sol Self Reflect + 2D Inspect Same-Region Closure (4-case)
  679. 2.00 CADGenBench submission lehuili_gpt-5-6-sol-two-stage-reflection-post-ed_20260822-092931: GPT-5.6 Sol Two-Stage Reflection + Post-Edit Acceptance Closed Loop (4-case)
  680. 2.00 CADGenBench submission wolf_pi-agent-4cases_20260908-083746: pi-agent-4cases
  681. 1.99 CADGenBench submission arisa_gpt-5-6-sol-step-wise-strategy-v1-r3-101_20260914-114625: GPT-5.6-sol-step-wise-strategy-v1-r3-101-102-103-128
  682. 1.99 CADGenBench submission cad-edit-test_test-5-samples_20261011-103623: test-5-samples
  683. 1.98 CADGenBench submission lehuili_gpt-5-6-sol-main-agent-self-reflect-4-ca_20260821-122617: GPT-5.6 Sol Main Agent Self Reflect (4-case)
  684. 1.97 CADGenBench submission cad-mcp-research_inspection-first-development-cell-5019c5_20260823-010251: inspection-first development cell-5019c5b12d6b90ed5ca4
  685. 1.97 CADGenBench submission anonymous_anon-gen-1787964075-a10f_20260829-004116: anon-gen-1787964075-a10f
  686. 1.97 CADGenBench submission anonymous_anon-gen-1787968204-52a0_20260829-015005: anon-gen-1787968204-52a0
  687. 1.97 CADGenBench submission yitong42_matched-baseline-codex-gpt-5-6-sol-high-_20260906-112731: Matched baseline + Codex gpt-5.6-sol high (4-case)
  688. 1.95 CADGenBench submission one-research_gpt-5-6-sol-v9-pi-agent-r3-101-102-103-1_20260913-135330: GPT-5.6-sol-v9-pi-agent-r3-101-102-103-128
  689. 1.94 CADGenBench submission cad-mcp-research_inspection-first-comparison-cell-4519f7a_20260824-054754: inspection-first comparison cell-4519f7a9003e08c7496f
  690. 1.94 CADGenBench submission one-research_gpt-5-6-sol-no-steps_20260910-113355: GPT-5.6-sol-no_steps
  691. 1.93 CADGenBench submission pzfreo_opus5-xhigh-direct-build123d-nomcp-pilot_20260809-174214: opus5-xhigh-direct-build123d-nomcp-pilot2-partial
  692. 1.93 CADGenBench submission anonymous_anon-gen-1788135167-b8ef_20260831-001249: anon-gen-1788135167-b8ef
  693. 1.93 CADGenBench submission one-research_gpt-5-6-sol-steps-rerun_20260910-145136: GPT-5.6-sol-steps-rerun
  694. 1.92 CADGenBench submission lehuili_gpt-5-6-sol-view-search-dual-roi-reflect_20260821-122637: GPT-5.6 Sol View Search + Dual-ROI Reflection (4-case)
  695. 1.92 CADGenBench submission cad-mcp-research_inspection-first-development-cell-6a3b89_20260823-011256: inspection-first development cell-6a3b898bb8fa83f8fb18
  696. 1.92 CADGenBench submission one-research_gpt-5-6-sol-steps_20260910-113415: GPT-5.6-sol-steps
  697. 1.91 CADGenBench submission pzfreo_gpt55-v0372-smoke5_20260707-195934: gpt55-v0372-smoke5
  698. 1.91 CADGenBench submission pzfreo_gpt55-v0372-smoke5-r2_20260707-203158: gpt55-v0372-smoke5-r2
  699. 1.90 CADGenBench submission one-research_gpt-5-6-sol-v9-pi-agent-r1-101-102-103-1_20260913-134652: GPT-5.6-sol-v9-pi-agent-r1-101-102-103-128
  700. 1.87 CADGenBench submission lehuili_gpt-5-6-sol-self-reflect-two-stage-refle_20260821-155434: GPT-5.6 Sol Self Reflect + Two-Stage Reflection (4-case)
  701. 1.87 CADGenBench submission lehuili_gpt-5-6-sol-view-search-no-crop-reflecti_20260821-122543: GPT-5.6 Sol View Search + No-Crop Reflection (4-case)
  702. 1.86 CADGenBench submission one-research_gpt-5-6-sol-v9-step-r1-101-102-103-128_20260913-135351: GPT-5.6-sol-v9-step-r1-101-102-103-128
  703. 1.85 CADGenBench submission local-user_t047-m1x1-t-20261028_20261028-054234: t047-m1x1-t-20261028
  704. 1.84 CADGenBench submission yitong42_svg-first-codex-gpt-5-6-sol-high-4-case-_20260905-102720: SVG-first Codex + gpt-5.6-sol high (4-case diagnostic)
  705. 1.83 CADGenBench submission lehuili_gpt-5-6-sol-main-agent-direct-4-case_20260821-122554: GPT-5.6 Sol Main Agent Direct (4-case)
  706. 1.81 CADGenBench submission lehuili_gpt-5-6-sol-main-agent-fixed-view-2d-sel_20260821-162630: GPT-5.6 Sol Main Agent Fixed-View 2D Self-Reflection (4-case)
  707. 1.80 CADGenBench submission lehuili_gpt-5-6-sol-atomic-geometry-repair-4-cas_20260908-162606: GPT-5.6 Sol Atomic Geometry Repair (4-case, 2026-09-08)
  708. 1.79 CADGenBench submission one-research_gpt-5-6-sol-v9-pi-agent-r2-101-102-103-1_20260913-135255: GPT-5.6-sol-v9-pi-agent-r2-101-102-103-128
  709. 1.78 CADGenBench submission local-user_t047-r3-p2-r02-20261027_20261027-082405: t047-r3-p2-r02-20261027
  710. 1.77 CADGenBench submission anonymous_cadgenbench-111-148-test-2_20260905-132001: CADGenBench 111+148 test 2
  711. 1.77 CADGenBench submission one-research_gpt-5-6-sol-no-steps-rerun_20260910-145542: GPT-5.6-sol-no_steps-rerun
  712. 1.74 CADGenBench submission local-user_t047-r3-b-r03-20261027_20261027-082224: t047-r3-b-r03-20261027
  713. 1.74 CADGenBench submission local-user_t051-r010-b1-b_20261102-185656: t051-r010-b1-b
  714. 1.72 CADGenBench submission anonymous_h45-a1-partial_20261021-111114: H45-A1 (partial)
  715. 1.72 CADGenBench submission local-user_t047-r3-b-r02-20261027_20261027-082132: t047-r3-b-r02-20261027
  716. 1.72 CADGenBench submission numafi-7095_gen2-numafi-7095_20261102-203546: gen2-numafi-7095
  717. 1.71 CADGenBench submission local-user_t047-tool021-diag-t-r2-20261029_20261029-025013: t047-tool021-diag-t-r2-20261029
  718. 1.70 CADGenBench submission local-user_t047-r3-p2-r03-20261027_20261027-082506: t047-r3-p2-r03-20261027
  719. 1.70 CADGenBench submission local-user_t051-r008-c_20261102-092933: t051-r008-c
  720. 1.69 CADGenBench submission one-research_gpt-5-6-sol-v9-step-r2-101-102-103-128_20260913-135407: GPT-5.6-sol-v9-step-r2-101-102-103-128
  721. 1.68 CADGenBench submission lehuili_gpt-5-6-sol-main-edit-preview-4-case-202_20260909-030433: GPT-5.6 Sol Main Edit Preview (4-case, 2026-09-09)
  722. 1.68 CADGenBench submission local-user_t047-m1x1-c-20261028_20261028-054131: t047-m1x1-c-20261028
  723. 1.66 CADGenBench submission cad-mcp-research_inspection-first-development-cell-8b3b68_20260823-013718: inspection-first development cell-8b3b6875fd8deb1620d0
  724. 1.65 CADGenBench submission cadgenbench-reflection-study_pi-kimi-k3-reflection-after-102-103-145_20260815-104735: Pi Kimi K3 Reflection AFTER 102 103 145
  725. 1.63 CADGenBench submission cadgenbench-reflection-study_pi-kimi-k3-incremental-editable-reflecti_20260816-202605: Pi Kimi K3 Incremental Editable Reflection Guided 102 103 145
  726. 1.62 CADGenBench submission local-user_t047-d1-a-r01-20261027_20261027-162140: t047-d1-a-r01-20261027
  727. 1.61 CADGenBench submission cadgenbench-reflection-study_pi-kimi-k3-post-submit-dual-roi-reflecti_20260817-033318: Pi Kimi K3 Post-Submit Dual ROI Reflection Guided 102 103 145
  728. 1.60 CADGenBench submission lehuili_gpt-5-6-sol-optional-reflect-causal-repa_20260822-145641: GPT-5.6 Sol Optional Reflect + Causal Repair (4-case)
  729. 1.60 CADGenBench submission local-user_t047-d2g-d3e-c-r01-20261028_20261028-014901: t047-d2g-d3e-c-r01-20261028
  730. 1.60 CADGenBench submission local-user_t047-d2g-d3e-c-r02-20261028_20261028-015028: t047-d2g-d3e-c-r02-20261028
  731. 1.60 CADGenBench submission local-user_t047-d2g-d3e-t-r01-20261028_20261028-015139: t047-d2g-d3e-t-r01-20261028
  732. 1.60 CADGenBench submission local-user_t047-d2g-d3e-t-r02-20261028_20261028-015222: t047-d2g-d3e-t-r02-20261028
  733. 1.59 CADGenBench submission cadgenbench-reflection-study_pi-kimi-k3-dual-roi-reflection-guided-10_20260816-151158: Pi Kimi K3 Dual ROI Reflection Guided 102 103 145
  734. 1.56 CADGenBench submission anonymous_anon-gen-1788070413-8f87_20260830-061334: anon-gen-1788070413-8f87
  735. 1.54 CADGenBench submission lindacyffan_pi-agent-qwen3-8-steps-101-103-118_20260906-144933: Pi Agent - Qwen3.8-steps- 101+103+118
  736. 1.53 CADGenBench submission cadgenbench-reflection-study_pi-kimi-k3-verified-dual-roi-reflection-_20260816-175950: Pi Kimi K3 Verified Dual ROI Reflection Guided 102 103 145
  737. 1.53 CADGenBench submission anonymous_anon-edit-1787967797-0357_20260829-014318: anon-edit-1787967797-0357
  738. 1.52 CADGenBench submission paramancer_paramancer-build123d-mcp-0-3-85-dev0-gpt_20261017-123044: paramancer-build123d-mcp-0.3.85.dev0-gpt-6.1-sol-high-pilot-20261017
  739. 1.47 CADGenBench submission yitong42_codex-gpt-5-6-sol-high-4-case-baseline_20260905-104105: Codex + gpt-5.6-sol high (4-case baseline)
  740. 1.44 CADGenBench submission cadgenbench-reflection-study_pi-kimi-k3-reflection-before-102-103-145_20260815-104640: Pi Kimi K3 Reflection BEFORE 102 103 145
  741. 1.44 CADGenBench submission cadgenbench-reflection-study_pi-kimi-k3-optional-dual-roi-reflection-_20260816-143854: Pi Kimi K3 Optional Dual ROI Reflection 102 103 145
  742. 1.42 CADGenBench submission reify_reify-gpt-6-1-sol-low-101-201-pilot_20261021-080035: Reify GPT-6.1 Sol low - 101 201 pilot
  743. 1.41 CADGenBench submission zky_pi-agent-glm-5-3-flash-fixtures-101-102-_20260902-034512: Pi Agent GLM-5.3-Flash fixtures 101-102-103-111
  744. 1.41 CADGenBench submission lindacyffan_pi-agent-qwen3-8-101-103-118_20260906-144715: Pi Agent - Qwen3.8- 101+103+118
  745. 1.38 CADGenBench submission anonymous_anon-edit-1787966903-ab75_20260829-012824: anon-edit-1787966903-ab75
  746. 1.37 CADGenBench submission reify-evaluation_reify-0-1-1-gpt-5-6-sol-medium-hardest10_20261012-043910: Reify 0.1.1 gpt-5.6-sol medium hardest10 partial3 20261011
  747. 1.36 CADGenBench submission cadgenbench-reflection-study_pi-kimi-k3-main-agent-self-reflect-102-1_20260815-142707: Pi Kimi K3 Main Agent Self Reflect 102 103 145
  748. 1.33 CADGenBench submission cadgenbench-reflection-study_pi-kimi-k3-fixed-grid-reflection-guided-_20260816-222358: Pi Kimi K3 Fixed Grid Reflection Guided 102 103 145
  749. 1.28 CADGenBench submission verdigris_verdigris_20260909-221559: verdigris
  750. 1.26 CADGenBench submission local-user_t047-tool021-diag-c-r2-20261029_20261029-024933: t047-tool021-diag-c-r2-20261029
  751. 1.22 CADGenBench submission zky_pi-agent-steps-qwen3-8-103-118_20260906-044155: Pi Agent + steps - Qwen3.8-103 + 118
  752. 1.22 CADGenBench submission arisa_gpt-5-6-sol-step-wise-strategy-v1-increm_20260915-053748: GPT-5.6-sol-step-wise-strategy-v1-incremental-visual-check-r1-102-103
  753. 1.21 CADGenBench submission gkgyc233_a-test-of-one-sample-on-gpt-6-astra_20260907-113058: A test of one sample on GPT 6 Astra
  754. 1.20 CADGenBench submission anonymous_anon-edit-1788298205-22f6_20260901-213006: anon-edit-1788298205-22f6
  755. 1.20 CADGenBench submission anonymous_anon-gen-1788803033-562e4d_20260907-174354: anon-gen-1788803033-562e4d
  756. 1.20 CADGenBench submission lindacyffan_pi-agent-qwen3-8-115-128_20260907-045804: Pi Agent - Qwen3.8-115+128
  757. 1.20 CADGenBench submission anonymous_anon-gen-1789083011-74e9e3_20260911-010046: anon-gen-1789083011-74e9e3
  758. 1.20 CADGenBench submission reify-evaluation_reify-user-rerun-hardest10-203-20261012_20261012-045422: Reify user rerun hardest10 203 20261012
  759. 1.19 CADGenBench submission wolf_cadgenresearchs-102-103_20260907-110054: CADgenResearchs-102+103
  760. 1.18 CADGenBench submission zky_pi-agent-qwen3-8-103-118_20260906-042924: Pi Agent Qwen3.8-103 + 118
  761. 1.17 CADGenBench submission yitong42_pi-agent-gpt-5-6-sol-high-3-sample-diagn_20260808-093153: Pi Agent + gpt-5.6-sol high (3-sample diagnostic)
  762. 1.17 CADGenBench submission zky_pi-agent-glm-5-3-flash-fixtures-101-102-_20260902-023005: Pi Agent GLM-5.3-Flash fixtures 101-102-111
  763. 1.17 CADGenBench submission yitong42_codex-gpt-6-astra-ultra-baseline-case-10_20260906-160657: Codex GPT-6 Astra Ultra baseline (case 102)
  764. 1.17 CADGenBench submission cadse_gemma-4-e4b-local-4b-drawing-api-idioms-_20261112-093017: Gemma-4-E4B (local, 4B): drawing + API idioms + check loop, first valid of three arms per part, 9 random fixtures (seed 20261112)
  765. 1.16 CADGenBench submission jake-fitzgerald_codex-build123d-first3-validation_20260609-112054: Codex build123d first3 validation
  766. 1.16 CADGenBench submission zky_pi-agent-qwen3-8-101-103_20260903-115005: Pi Agent Qwen3.8-101+103
  767. 1.15 CADGenBench submission arisa_gpt-5-6-sol-visual-check-oneshot-101-ste_20260915-080620: GPT-5.6-sol-visual-check-oneshot-101-step-128-r1
  768. 1.14 CADGenBench submission independent-cad-workflow_blind-fixture-215-end-disc-thickness-1-t_20260815-095040: Blind fixture 215 end disc thickness 1 to 2 run001
  769. 1.13 CADGenBench submission w1ne_kernelcad-probe-tiny-20261019_20261019-150640: kernelcad-probe-tiny-20261019
  770. 1.13 CADGenBench submission reify_reify-deepseek-low-naked-215-export-fix-_20261022-091801: reify-deepseek-low-naked-215-export-fix-01
  771. 1.12 CADGenBench submission jake-fitzgerald_codex-cad-skill-first3-validation_20260609-105454: Codex cad skill first3 validation
  772. 1.09 CADGenBench submission wolf_cadgenresearch-102-103_20260907-105849: CADgenResearch-102+103
  773. 1.09 CADGenBench submission cad-experiment_two-task-cad-experiment-120-241_20260916-005258: Two-task CAD experiment (120, 241)
  774. 1.07 CADGenBench submission draw2cad_draw2cad-drawing-derived-101-2026-09-13_20260912-155517: draw2cad drawing-derived 101 2026-09-13
  775. 1.06 CADGenBench submission yitong42_codex-gpt-5-6-sol-high-3-sample-diagnost_20260808-084612: Codex + gpt-5.6-sol high (3-sample diagnostic)
  776. 1.06 CADGenBench submission independent-cad-workflow_blind-fixture-214-edit-run001_20260813-125249: Blind fixture 214 edit run001
  777. 1.06 CADGenBench submission cad-mcp-research_canonical-frame-v0-3-17-task105-diagnost_20260823-234206: canonical-frame v0.3.17 task105 diagnostic cell-e24ead3d40780c161662
  778. 1.05 CADGenBench submission independent-cad-workflow_blind-fixture-224-edit-run001_20260813-133148: Blind fixture 224 edit run001
  779. 1.05 CADGenBench submission anonymous_anon-gen-1789073510-472d47_20260910-205208: anon-gen-1789073510-472d47
  780. 1.05 CADGenBench submission xyz_gpt-5-6-sol-incremental-v1-generic-stage_20260918-062517: GPT-5.6-sol-incremental-v1-generic-stages-v2-high-step-101-102-r1
  781. 1.02 CADGenBench submission lindacyffan_pi-agent-qwen3-8-steps-115-128_20260907-045831: Pi Agent - Qwen3.8-steps-115+128
  782. 1.00 CADGenBench submission mix_20260920-gpt-5-6-sol-mix-step-101-xhigh-_20260920-142607: 20260920-GPT-5.6-sol-mix-step-101-xhigh-102-high-r1
  783. 0.99 CADGenBench submission mliu_chamfer-cad-harness-0-1-2-dev2_20260707-071439: chamfer-cad-harness-0.1.2.dev2
  784. 0.98 CADGenBench submission anonymous_anon-gen-1789073510-1ff981_20260910-210109: anon-gen-1789073510-1ff981
  785. 0.96 CADGenBench submission o-uz_o-uz-chatgpt-build123d-task-109-pilot-v0_20260817-123006: OĞUZ ChatGPT-build123d Task 109 Pilot v0.1
  786. 0.94 CADGenBench submission yitong42_codex-gpt-6-astra-ultra-self-reconstruct_20260906-161753: Codex GPT-6 Astra Ultra self-reconstructed SVG-CAD (case 102)
  787. 0.93 CADGenBench submission lindacyffan_pi-agent-qwen3-8-128_20260907-031448: Pi Agent - Qwen3.8-128
  788. 0.92 CADGenBench submission xyz_gpt-5-6-sol-oneshot-visual-check-high-10_20260918-062536: GPT-5.6-sol-oneshot-visual-check-high-101-102-r1
  789. 0.91 CADGenBench submission lindacyffan_cadresearch-128_20260907-091307: CADResearch-128
  790. 0.91 CADGenBench submission high_20260920-gpt-5-6-sol-incremental-v1-gene_20260920-123924: 20260920-GPT-5.6-sol-incremental-v1-generic-stages-v2-high-step-101-r2
  791. 0.90 CADGenBench submission mliu_chamfer-cad-harness-0-1-2-dev2_20260707-085910: chamfer-cad-harness-0.1.2.dev2
  792. 0.90 CADGenBench submission lindacyffan_cadresearch-steps-128_20260907-091409: CADResearch-steps-128
  793. 0.89 CADGenBench submission anonymous_anon-edit-1788072384-a74e_20260830-064625: anon-edit-1788072384-a74e
  794. 0.89 CADGenBench submission zky_pi-agent-glm-5-3-flash-fixtures-101-103_20260902-064301: Pi Agent GLM-5.3-Flash fixtures 101-103
  795. 0.89 CADGenBench submission xyz_20260920-gpt-5-6-sol-oneshot-visual-chec_20260920-073517: 20260920-GPT-5.6-sol-oneshot-visual-check-xhigh-102-143-r1
  796. 0.86 CADGenBench submission xyz_20260920-gpt-5-6-sol-incremental-v1-gene_20260920-073552: 20260920-GPT-5.6-sol-incremental-v1-generic-stages-v2-xhigh-step-102-143-r1
  797. 0.85 CADGenBench submission lindacyffan_pi-agent-qwen3-8-steps-128_20260907-031554: Pi Agent - Qwen3.8-steps-128
  798. 0.85 CADGenBench submission anonymous_anon-gen-1789083011-300e52_20260911-005533: anon-gen-1789083011-300e52
  799. 0.85 CADGenBench submission origogk_origogk-diagnostic-149-voxel-1mm_20260925-153940: OrigoGK diagnostic 149 voxel-1mm
  800. 0.84 CADGenBench submission independent-cad-workflow_blind-fixture-211-top-surface-10-run001_20260815-091450: Blind fixture 211 top surface +10 run001
  801. 0.83 CADGenBench submission cad-mcp-research_axis-grounded-review-v0-3-8-task105-diag_20260823-203421: axis-grounded-review v0.3.8 task105 diagnostic cell-27fc476f16350bcadf75
  802. 0.83 CADGenBench submission local-user_t047-repair-b-103-20261027_20261027-120251: t047-repair-b-103-20261027
  803. 0.82 CADGenBench submission cad-mcp-research_topology-grounded-v0-3-4-diagnostic-cell_20260823-162546: topology-grounded v0.3.4 diagnostic cell-7c368edcabea6bab12ae
  804. 0.79 CADGenBench submission cad-mcp-research_visual-source-review-v0-3-6-task105-diag_20260823-193859: visual-source-review v0.3.6 task105 diagnostic cell-20f0e795affaafcc30b0
  805. 0.78 CADGenBench submission anonymous_anon-edit-1788156537-2756_20260831-060858: anon-edit-1788156537-2756
  806. 0.78 CADGenBench submission mix_20260920-gpt-5-6-sol-mix-oneshot-101-xhi_20260920-142541: 20260920-GPT-5.6-sol-mix-oneshot-101-xhigh-102-high-r1
  807. 0.77 CADGenBench submission cad-mcp-research_stepped-port-semantics-v0-3-16-task105-d_20260823-224210: stepped-port-semantics v0.3.16 task105 diagnostic cell-a2c78183b51bec3444bd
  808. 0.77 CADGenBench submission zky_pi-agent-glm-5-3-flash-fixtures-101-102_20260901-155807: Pi Agent GLM-5.3-Flash fixtures 101-102
  809. 0.76 CADGenBench submission cadse_probe-flipx-part-150-of-the-lean-repeat-_20261112-082959: probe flipx: part 150 of the lean repeat turned 180 deg about X, pose test, 1 fixture
  810. 0.75 CADGenBench submission independent-cad-workflow_blind-fixture-132-run001_20260812-155030: Blind fixture 132 run001
  811. 0.75 CADGenBench submission cad-mcp-research_visual-source-review-v0-3-6-task105-diag_20260823-194437: visual-source-review v0.3.6 task105 diagnostic cell-397350b933b119cdb308
  812. 0.74 CADGenBench submission cad-mcp-research_topology-grounded-v0-3-4-diagnostic-cell_20260823-161915: topology-grounded v0.3.4 diagnostic cell-241c6c8e2c57645cbc93
  813. 0.74 CADGenBench submission local-user_t047-repair-p2-103-20261027_20261027-120454: t047-repair-p2-103-20261027
  814. 0.74 CADGenBench submission cadse_probe-rotz-part-150-of-the-lean-repeat-t_20261112-083034: probe rotz: part 150 of the lean repeat turned 180 deg about Z, pose test, 1 fixture
  815. 0.73 CADGenBench submission wolf_cadgenresearchs-103_20260908-023535: CADgenResearchs-103
  816. 0.72 CADGenBench submission cad-mcp-research_constraint-verified-v0-3-3-diagnostic-ce_20260823-143430: constraint-verified v0.3.3 diagnostic cell-b638afa5499f71d46e2b
  817. 0.72 CADGenBench submission cad-mcp-research_constraint-verified-v0-3-3-diagnostic-ce_20260823-144049: constraint-verified v0.3.3 diagnostic cell-1950efc045c9ce03d939
  818. 0.72 CADGenBench submission lindacyffan_pi-agent-qwen3-8-steps-102-143_20260907-020424: Pi Agent - Qwen3.8-steps- 102+143
  819. 0.71 CADGenBench submission cad-mcp-research_axis-grounded-review-v0-3-8-task105-diag_20260823-202617: axis-grounded-review v0.3.8 task105 diagnostic cell-10fb08d05b9706e8922a
  820. 0.71 CADGenBench submission zky_pi-agent-glm-5-3-flash-fixtures-103-free_20260902-104810: Pi Agent GLM-5.3-Flash fixtures 103（free）
  821. 0.71 CADGenBench submission zky_pi-agent-glm-5-3-flash-fixtures-103-free_20260902-124125: Pi Agent GLM-5.3-Flash fixtures 103（free-3）
  822. 0.71 CADGenBench submission lindacyffan_pi-agent-qwen3-8-102-143_20260907-020249: Pi Agent - Qwen3.8- 102+143
  823. 0.71 CADGenBench submission cadse_probe-d-part-150-of-the-hole-rules-run-w_20261112-084743: probe d: part 150 of the hole-rules run with the rear slope starting later, 1 fixture
  824. 0.70 CADGenBench submission cadse_probe-a-part-150-of-the-hole-rules-run-w_20261112-084610: probe a: part 150 of the hole-rules run with shorter floor slots, 1 fixture
  825. 0.70 CADGenBench submission cadse_probe-b-part-150-of-the-hole-rules-run-w_20261112-084704: probe b: part 150 of the hole-rules run with the 15 mm hole from the top face, 1 fixture
  826. 0.68 CADGenBench submission cad-mcp-research_inspection-first-diagnostic-cell-eefa0cc_20260824-015832: inspection-first diagnostic cell-eefa0cca2d7cf5523cdd
  827. 0.68 CADGenBench submission zky_pi-agent-qwen3-8-103_20260903-122207: Pi Agent Qwen3.8-103
  828. 0.64 CADGenBench submission reify_reify-deepseek-v4-1-flash-medium-assiste_20261021-062037: Reify DeepSeek v4.1 Flash medium - assisted 101 201 pilot
  829. 0.61 CADGenBench submission cad-mcp-research_stepped-port-semantics-v0-3-16-task105-d_20260823-225025: stepped-port-semantics v0.3.16 task105 diagnostic cell-cef4882a7ec02ae5312c
  830. 0.61 CADGenBench submission zky_pi-agent-glm-5-3-flash-fixtures-103-1_20260902-103111: Pi Agent GLM-5.3-Flash fixtures 103（1）
  831. 0.61 CADGenBench submission abc_gpt-5-6-sol-stage-ablation-baseline-v1-h_20260916-130122: GPT-5.6-sol-stage-ablation-baseline-v1-high-101
  832. 0.61 CADGenBench submission reify_reify-deepseek-low-asi-hard-edit-204-241_20261023-154259: reify-deepseek-low-asi-hard-edit-204-241-243-01
  833. 0.61 CADGenBench submission reify_reify-deepseek-low-naked-204-01_20261024-055930: reify-deepseek-low-naked-204-01
  834. 0.60 CADGenBench submission universe_20260920-gpt-5-6-sol-oneshot-visual-chec_20260920-083649: 20260920-GPT-5.6-sol-oneshot-visual-check-xhigh-101-r1
  835. 0.60 CADGenBench submission reify_reify-sol-low-naked-asi-201-comparison_20261021-160613: reify-sol-low-naked-asi-201-comparison
  836. 0.59 CADGenBench submission wolf_cadgenresearchs103_20260908-023513: CADgenResearchs103
  837. 0.59 CADGenBench submission niming_a-research_20261001-134447: a_research
  838. 0.57 CADGenBench submission abc_gpt-5-6-sol-stage-ablation-reread-v1-hig_20260916-130223: GPT-5.6-sol-stage-ablation-reread-v1-high-101
  839. 0.55 CADGenBench submission pzfreo_gpt55-v0377-xhigh-gen3-dominant_20260710-062829: gpt55-v0377-xhigh-gen3-dominant
  840. 0.54 CADGenBench submission lehuili_gpt-5-6-visual-findings-no-dual-roi-case_20260822-211640: GPT-5.6 Visual Findings No Dual ROI (Case 103)
  841. 0.54 CADGenBench submission lehuili_gpt-5-6-sol-optional-reflect-code-ablati_20260830-111204: GPT-5.6 Sol Optional Reflect + Code Ablation (Case 103)
  842. 0.54 CADGenBench submission amy_gpt-5-6-sol-incremental-v1-high-step-101_20260916-092831: GPT-5.6-sol-incremental-v1-high-step-101
  843. 0.53 CADGenBench submission charif_antigravity-build123d-agent_20260905-204201: Antigravity Build123d Agent
  844. 0.53 CADGenBench submission abc_gpt-5-6-sol-stage-ablation-focus-v1-high_20260916-130201: GPT-5.6-sol-stage-ablation-focus-v1-high-101
  845. 0.52 CADGenBench submission zky_pi-agent-glm-5-3-flash-fixtures-103-free_20260903-061910: Pi Agent GLM-5.3-Flash fixtures 103（free-1）
  846. 0.52 CADGenBench submission local-user_t046-cgb101-0770-local-v1_20261026-072818: t046-cgb101-0770-local-v1
  847. 0.51 CADGenBench submission pzfreo_gpt55-v0371-xhigh-tricky3-retry_20260707-122755: gpt55-v0371-xhigh-tricky3-retry
  848. 0.51 CADGenBench submission lehuili_gpt-5-6-optional-reflect-persistent-visu_20260822-204648: GPT-5.6 Optional Reflect + Persistent Visual Findings + 2D Completion (Case 103)
  849. 0.51 CADGenBench submission lehuili_gpt-5-6-sol-causal-repair-diverse-hypoth_20260822-170015: GPT-5.6 Sol Causal Repair Diverse Hypotheses (Case 103)
  850. 0.50 CADGenBench submission lindacyffan_pi-agent-qwen3-8-steps-115_20260907-064326: Pi Agent - Qwen3.8-steps-115
  851. 0.50 CADGenBench submission anonymous_anon-edi-1789088523-2764d8_20260911-010231: anon-edi-1789088523-2764d8
  852. 0.49 CADGenBench submission independent-cad-workflow_blind-fixture-247-edit-run001_20260813-120356: Blind fixture 247 edit run001
  853. 0.49 CADGenBench submission nrocketmann_cad-agent-deep-build-probe-2-of-81-fixtu_20260831-231311: cad-agent Deep Build probe (2 of 81 fixtures)
  854. 0.49 CADGenBench submission pzfreo_build123d-mcp-0-3-85-dev0-opus-5-xhigh_20260904-183253: build123d-mcp-0.3.85.dev0-opus-5-xhigh
  855. 0.49 CADGenBench submission arisa_gpt-5-6-sol-step-wise-strategy-v1-increm_20260915-020357: GPT-5.6-sol-step-wise-strategy-v1-incremental-visual-check-r1-101
  856. 0.49 CADGenBench submission xyz_gpt-5-6-sol-incremental-v1-high-pi-agent_20260917-122313: GPT-5.6-sol-incremental-v1-high-pi-agent-103-r1
  857. 0.49 CADGenBench submission xyz_gpt-5-6-sol-incremental-v1-high-step-103_20260917-122339: GPT-5.6-sol-incremental-v1-high-step-103-r1
  858. 0.47 CADGenBench submission anonymous_anon-edit-1788239926-61c9_20260901-051847: anon-edit-1788239926-61c9
  859. 0.47 CADGenBench submission high_20260920-gpt-5-6-sol-oneshot-visual-chec_20260920-123853: 20260920-GPT-5.6-sol-oneshot-visual-check-high-101-r2
  860. 0.45 CADGenBench submission charif_antigravity-build123d_20260903-141338: Antigravity Build123d
  861. 0.45 CADGenBench submission anonymous_anon-edi-1789073510-b03ffd_20260910-210642: anon-edi-1789073510-b03ffd
  862. 0.45 CADGenBench submission abc_gpt-5-6-sol-stage-ablation-visual-loop-v_20260916-130238: GPT-5.6-sol-stage-ablation-visual-loop-v1-high-101
  863. 0.45 CADGenBench submission universe_20260920-gpt-5-6-sol-incremental-v1-gene_20260920-083614: 20260920-GPT-5.6-sol-incremental-v1-generic-stages-v2-xhigh-step-101-r1
  864. 0.45 CADGenBench submission cadgenbench-2d-to-3d_dxf-to-fusion-0-6-6-2-track-b-subset-150_20261012-142153: dxf-to-fusion 0.6.6.2 Track B subset (150/129/120)
  865. 0.44 CADGenBench submission version5_101-no-step-1_20260909-072608: 101-no_step-1
  866. 0.42 CADGenBench submission anonymous_anon-edit-1788135725-f790_20260831-002206: anon-edit-1788135725-f790
  867. 0.42 CADGenBench submission anonymous_anon-gen-1788292278-d51a_20260901-195119: anon-gen-1788292278-d51a
  868. 0.42 CADGenBench submission version5_101-step-2_20260909-072653: 101-_step-2
  869. 0.41 CADGenBench submission zky_pi-agent-glm-5-3-flash-fixtures-103_20260902-093620: Pi Agent GLM-5.3-Flash fixtures 103
  870. 0.41 CADGenBench submission wolf_101_20260908-050030: 101
  871. 0.40 CADGenBench submission zky_pi-agent-glm-5-3-flash-fixture-101_20260901-152620: Pi Agent GLM-5.3-Flash fixture 101
  872. 0.39 CADGenBench submission zky_pi-agent-qwen3-8-101_20260906-081914: Pi Agent - Qwen3.8-101
  873. 0.39 CADGenBench submission zky_pi-agent-steps-qwen3-8-101_20260906-081610: Pi Agent + steps - Qwen3.8-101
  874. 0.39 CADGenBench submission wolf_101-step_20260908-055041: 101+step
  875. 0.39 CADGenBench submission amy_gpt-5-6-sol-incremental-v1-high-pi-agent_20260916-092808: GPT-5.6-sol-incremental-v1-high-pi-agent-101
  876. 0.38 CADGenBench submission wolf_101-step_20260908-050131: 101-step
  877. 0.38 CADGenBench submission version5_101-no-step-2_20260909-072631: 101-no_step-2
  878. 0.38 CADGenBench submission version5_101-step-1_20260909-072729: 101-_step-1
  879. 0.37 CADGenBench submission independent-cad-workflow_blind-fixture-147-run001_20260812-143651: Blind fixture 147 run001
  880. 0.37 CADGenBench submission cad-mcp-research_inspection-first-diagnostic-cell-1dd2bf1_20260824-025803: inspection-first diagnostic cell-1dd2bf12c6601f0c9768
  881. 0.37 CADGenBench submission anonymous_cadgenbench-111-148-test_20260905-130419: CADGenBench 111+148 test
  882. 0.37 CADGenBench submission zky_pi-agent-qwen3-8-101_20260906-084559: Pi Agent - Qwen3.8- 101
  883. 0.37 CADGenBench submission zky_pi-agent-steps-qwen3-8-101_20260906-081537: Pi Agent + steps - Qwen3.8-101
  884. 0.37 CADGenBench submission abc_gpt-5-6-sol-incremental-v1-high-step-101_20260917-050510: GPT-5.6-sol-incremental-v1-high-step-101-r2
  885. 0.36 CADGenBench submission independent-cad-workflow_blind-fixture-105-generation-run001_20260820-133942: Blind fixture 105 generation run001
  886. 0.35 CADGenBench submission cad-mcp-research_inspection-first-diagnostic-cell-87cfd25_20260824-025121: inspection-first diagnostic cell-87cfd25994da8be2ca7b
  887. 0.35 CADGenBench submission anonymous_anon-gen-1788239802-e5be_20260901-051643: anon-gen-1788239802-e5be
  888. 0.35 CADGenBench submission anonymous_anon-gen-1788315559-f1d3_20260902-021920: anon-gen-1788315559-f1d3
  889. 0.35 CADGenBench submission anonymous_anon-gen-1788372413-975c_20260902-180654: anon-gen-1788372413-975c
  890. 0.35 CADGenBench submission anonymous_anon-gen-1788372526-ef78_20260902-180848: anon-gen-1788372526-ef78
  891. 0.34 CADGenBench submission cad-mcp-research_canonical-frame-v0-3-17-task105-diagnost_20260823-231225: canonical-frame v0.3.17 task105 diagnostic cell-129aea4b2a0da94083a2
  892. 0.34 CADGenBench submission abc_gpt-5-6-sol-incremental-v1-high-pi-agent_20260917-055601: GPT-5.6-sol-incremental-v1-high-pi-agent-101-r2
  893. 0.33 CADGenBench submission cad-mcp-research_inspection-first-diagnostic-cell-522bc3d_20260824-035018: inspection-first diagnostic cell-522bc3d7f43296e096fa
  894. 0.32 CADGenBench submission cad-mcp-research_baseline-protected-v0-7-9-diagnostic-cel_20260824-151012: baseline-protected v0.7.9 diagnostic cell-de8b1f53d7d7f7d8bd2d
  895. 0.32 CADGenBench submission reify_reify-deepseek-v4-1-flash-low-asi-201-pi_20261021-131436: reify-deepseek-v4-1-flash-low-asi-201-pilot
  896. 0.31 CADGenBench submission anonymous_anon-r1_20260914-093726: anon-r1
  897. 0.30 CADGenBench submission independent-cad-workflow_blind-fixture-135-run001_20260812-110543: Blind fixture 135 run001
  898. 0.30 CADGenBench submission cad-mcp-research_baseline-protected-v0-7-9-diagnostic-cel_20260824-152358: baseline-protected v0.7.9 diagnostic cell-3b76b44215889537685b
  899. 0.30 CADGenBench submission cad-mcp-research_inspection-first-diagnostic-cell-390e124_20260824-040229: inspection-first diagnostic cell-390e1241465919b85df2
  900. 0.30 CADGenBench submission lindacyffan_pi-agent-qwen3-8-115_20260907-064412: Pi Agent - Qwen3.8-115
  901. 0.29 CADGenBench submission cad-mcp-research_visual-source-review-v0-3-6-task108-diag_20260823-192923: visual-source-review v0.3.6 task108 diagnostic cell-e4ee681e0ee6afde0895
  902. 0.28 CADGenBench submission cad-mcp-research_canonical-frame-v0-3-17-task112-diagnost_20260824-002039: canonical-frame v0.3.17 task112 diagnostic cell-e83020eae58980dc6d1b
  903. 0.28 CADGenBench submission cad-mcp-research_inspection-first-diagnostic-cell-309f7a3_20260824-030425: inspection-first diagnostic cell-309f7a37fc4fda81d9c4
  904. 0.27 CADGenBench submission wolf_101-pi-agent_20260908-054958: 101+pi-agent
  905. 0.26 CADGenBench submission cad-mcp-research_inspection-first-diagnostic-cell-9c5dd79_20260824-031058: inspection-first diagnostic cell-9c5dd797047d13334d3f
  906. 0.24 CADGenBench submission cad-mcp-research_topology-grounded-v0-3-4-task108-diagnos_20260823-170624: topology-grounded v0.3.4 task108 diagnostic cell-110a7bc4f6be74849f52
  907. 0.24 CADGenBench submission cad-mcp-research_canonical-frame-v0-3-17-task112-diagnost_20260824-001136: canonical-frame v0.3.17 task112 diagnostic cell-e7ff97b17c58e72daddb
  908. 0.23 CADGenBench submission cad-mcp-research_source-reinspection-v0-3-5-task108-diagn_20260823-180206: source-reinspection v0.3.5 task108 diagnostic cell-a1bdca8fc9a8516db2df
  909. 0.23 CADGenBench submission cad-mcp-research_visual-source-review-v0-3-6-task108-diag_20260823-185916: visual-source-review v0.3.6 task108 diagnostic cell-7a3944ae3ceafbce8064
  910. 0.23 CADGenBench submission cad-mcp-research_inspection-first-diagnostic-cell-72c16d1_20260824-031720: inspection-first diagnostic cell-72c16d112fb989a8fe48
  911. 0.19 CADGenBench submission michaelr27_pipeline-smoke-test-box_20260627-135608: Pipeline smoke test (box)
  912. 0.18 CADGenBench submission cad-mcp-research_canonical-frame-v0-3-17-task108-diagnost_20260823-235239: canonical-frame v0.3.17 task108 diagnostic cell-538fe6617610d443d89f
  913. 0.16 CADGenBench submission cad-mcp-research_source-reinspection-v0-3-5-task108-diagn_20260823-175319: source-reinspection v0.3.5 task108 diagnostic cell-847743c3b96ae944b081
  914. 0.15 CADGenBench submission draw2cad_draw2cad-wiring-smoke-2026-09-06_20260906-141211: draw2cad wiring smoke 2026-09-06
  915. 0.14 CADGenBench submission cad-mcp-research_topology-grounded-v0-3-4-task108-diagnos_20260823-170052: topology-grounded v0.3.4 task108 diagnostic cell-98e3f7952ceed293cf36
  916. 0.11 CADGenBench submission local-test_fake-mesh-upload-smoke-test_20260612-063710: Fake mesh upload smoke test
  917. 0.08 CADGenBench submission reify_reify-sol-low-naked-201-comparison_20261021-160213: reify-sol-low-naked-201-comparison
  918. 0.0 CADGenBench submission cad-mcp-research_canonical-frame-v0-3-17-task108-diagnost_20260823-235844: canonical-frame v0.3.17 task108 diagnostic cell-84cac741adb0ef74a571
  1. 1 CADGenBench submission godela_godela-modernized-agentic_20261109-183706: Godela - Modernized Agentic version 0.1.0; validated 85.1%
  2. 2 CADGenBench submission standard-manufacturing-co_smc-harness-fable-5-2-max_20261111-165655: SMC Harness + Fable 5.2 Max version 0.1.0; unvalidated 85.1%
  3. 3 CADGenBench submission deeprd_deeprd-v2_20261011-092629: deeprd-v2 version 0.1.0; unvalidated 84.8%
  4. 4 CADGenBench submission rexl2018_vextcad-vxl-agent-r1_20261107-142023: VextCAD VXL agent (r1) version 0.1.0; unvalidated 84.4%
  5. 5 CADGenBench submission deeprd_deeprd_20261011-060231: deeprd version 0.1.0; unvalidated 83.7%
  6. 6 CADGenBench submission muhammed-ikbal-arikan_arikan-siemens-nx-mcp-claude-opus-5-5_20261006-044721: Arikan_Siemens_NX_MCP + Claude Opus 5.5 version 0.1.0; unvalidated 83.5%
  7. 7 CADGenBench submission nik6_cad-ai-v11-4_20261014-200204: CAD AI V11.4 version 0.1.0; unvalidated 83.2%
  8. 8 CADGenBench submission pzfreo_build123d-mcp-0-3-85-mcp-server-claude-o_20260924-101549: build123d-mcp 0.3.85 MCP server + Claude Opus 5.5 (max effort) r2 version 0.1.0; validated 83%
  9. 9 CADGenBench submission nik6_cad-ai-v11-3_20261014-184426: CAD AI V11.3 version 0.1.0; unvalidated 82.9%
  10. 10 CADGenBench submission nik6_cad-ai-v11-all81-four-editing-reruns-opu_20261014-151205: CAD AI V11 all81 four editing reruns (Opus5.5) version 0.1.0; unvalidated 82.9%
  11. 11 CADGenBench submission nik6_cad-ai-v11-all81-fresh149-rerun-opus5-5_20261014-164341: CAD AI V11 all81 fresh149 rerun (Opus5.5) version 0.1.0; unvalidated 82.9%
  12. 12 CADGenBench submission nik6_cad-ai-v11-2_20261014-180126: CAD AI V11.2 version 0.1.0; unvalidated 82.9%
  13. 13 CADGenBench submission pzfreo_build123d-mcp-0-3-90-mcp-server-claude-o_20260926-100215: build123d-mcp 0.3.90 MCP server + Claude Opus 5.5 (max effort) R2.3 version 0.1.0; unvalidated 82.7%
  14. 14 CADGenBench submission symge_symge-claude-opus-5-5-agentic-hybrid_20260926-113258: Symge - Claude Opus 5.5: agentic hybrid version 0.1.0; unvalidated 82.6%
  15. 15 CADGenBench submission mechanical-reasoning_mechanical-reasoning-astra-xhigh_20261016-220931: Mechanical Reasoning — Astra xhigh version 0.1.0; unvalidated 82.4%
  16. 16 CADGenBench submission pzfreo_build123d-mcp-0-3-86-mcp-server-claude-o_20260925-194429: build123d-mcp 0.3.86 MCP server + Claude Opus 5.5 (max effort) R2.2 version 0.1.0; unvalidated 82.4%
  17. 17 CADGenBench submission mechanical-reasoning_mechanical-reasoning-astra-xhigh_20261017-024229: Mechanical Reasoning — Astra xhigh version 0.1.0; unvalidated 82.2%
  18. 18 CADGenBench submission nik6_cad-ai-v11-all81-four-checkpoint-repairs_20261014-021956: CAD AI V11 all81 four checkpoint repairs (Opus 5.5) version 0.1.0; unvalidated 82.2%
  19. 19 CADGenBench submission atomic_atomic-cad-v3_20261102-200731: Atomic CAD v3 version 0.1.0; unvalidated 82%
  20. 20 CADGenBench submission pzfreo_build123d-mcp-0-3-90-claude-sonnet-5-5-m_20260929-151832: build123d MCP 0.3.90 + Claude Sonnet 5.5 (Max) version 0.1.0; unvalidated 81.8%
  21. 21 CADGenBench submission pzfreo_build123d-mcp-0-3-85-mcp-server-claude-o_20260924-093300: build123d-mcp 0.3.85 MCP server + Claude Opus 5.5 (max effort) version 0.1.0; unvalidated 81.8%
  22. 22 CADGenBench submission godela_godela_20260915-045120: Godela version 0.1.0; validated 81.1%
  23. 23 CADGenBench submission nik6_cad-ai-v11-all-81-complete-opus-5-5_20261013-023932: CAD AI V11 all 81 complete (Opus 5.5) version 0.1.0; unvalidated 80.7%
  24. 24 CADGenBench submission xueqinglin_gpt-6-astra-claude-code-20260917-104819_20260917-025938: gpt-6-astra_claude-code_20260917-104819 version 0.1.0; unvalidated 80.6%
  25. 25 CADGenBench submission pzfreo_build123d-mcp-0-3-84-mcp-server-claude-o_20260923-092859: build123d-mcp 0.3.84 MCP server + Claude Opus 5.5 (xhigh effort) version 0.1.0; unvalidated 80.5%
  26. 26 CADGenBench submission cadse_generation-v2-editing-brief-v2_20261112-175916: generation v2 + editing brief v2 version 0.1.0; unvalidated 79.7%
  27. 27 CADGenBench submission anonymous_anon-all-1788919650-351ecb_20260909-020747: anon-all-1788919650-351ecb version 0.1.0; unvalidated 79.2%
  28. 28 CADGenBench submission cadse_v5-edits-full-run-v2-plus-31-built-edits_20261112-155101: v5 edits: full run v2 plus 31 built edits version 0.1.0; unvalidated 78.1%
  29. 29 CADGenBench submission nik6_cad-ai-v11-full-benchmark-opus-5-5_20261011-213229: CAD AI V11 full benchmark (Opus 5.5) version 0.1.0; unvalidated 76.9%
  30. 30 CADGenBench submission atomic_atomic-cad-v2_20261022-043132: Atomic CAD v2 version 0.1.0; unvalidated 76.8%
  31. 31 CADGenBench submission atomic_atomic-cad-v2_20261022-072149: Atomic CAD v2 version 0.1.0; unvalidated 76.8%
  32. 32 CADGenBench submission zone404mars_zone-404-mars-freecad-harness-claude-opu_20261112-145855: Zone 404 Mars Freecad harness + Claude Opus 5.5 xhigh version 0.1.0; unvalidated 76.6%
  33. 33 CADGenBench submission nik6_nik6-harness-v9-claude-opus-5-5-high-eff_20261001-233943: nik6-harness-v9 + Claude Opus 5.5 (high effort) version 0.1.0; unvalidated 76.2%
  34. 34 CADGenBench submission tracycui_gpt-6-astra-high-hf-baseline-with-build1_20261023-031459: GPT-6 Astra high HF baseline with build123d version 0.1.0; unvalidated 75.5%
  35. 35 CADGenBench submission pzfreo_claude-opus-5-5-xhigh-effort-official-ba_20260923-174740: Claude Opus 5.5 (xhigh effort), official baseline prompt version 0.1.0; unvalidated 75.2%
  36. 36 CADGenBench submission eren_symge-claude-opus-5-5_20260926-072929: Symge - Claude Opus 5.5 version 0.1.0; unvalidated 75.2%
  37. 37 CADGenBench submission atomic_atomic-cad-v1_20261018-043044: Atomic CAD v1 version 0.1.0; unvalidated 74.7%
  38. 38 CADGenBench submission rexl2018_vextor-vxl-agent-r6_20261106-141850: Vextor VXL agent (r6) version 0.1.0; unvalidated 73.1%
  39. 39 CADGenBench submission faber-ai_faber-ai-gpt6_20260906-132046: Faber AI - gpt6 version 0.1.0; unvalidated 71.6%
  40. 40 CADGenBench submission pzfreo_build123d-mcp-0-3-85-dev0-with-gpt-6-ast_20260905-073202: build123d-mcp 0.3.85.dev0 with GPT-6 Astra (High) version 0.1.0; unvalidated 71.5%
  41. 41 CADGenBench submission wormo_build123d-mcp-0-3-85-dev0-gpt-6-astra-xh_20261030-034033: build123d-mcp-0.3.85.dev0-gpt-6-astra-xhigh-supplement-202-240-20261030 version 0.1.0; unvalidated 71.3%
  42. 42 CADGenBench submission thomwolf_gpt-6-astra-high-cadgenbench-baseline-mi_20260909-144301: GPT-6 Astra (high) + CADGenBench baseline - missing retry 5 version 0.1.0; unvalidated 71.1%
  43. 43 CADGenBench submission rexl2018_vextor-vxl-agent-r5_20261105-143509: Vextor VXL agent (r5) version 0.1.0; unvalidated 70.9%
  44. 44 CADGenBench submission modelcorp_baseline-astra-codex-low-v1_20260905-013922: baseline-astra-codex-low-v1 version 0.1.0; unvalidated 70.5%
  45. 45 CADGenBench submission wormo_build123d-mcp-0-3-85-dev0-gpt-6-astra-xh_20261030-013513: build123d-mcp-0.3.85.dev0-gpt-6-astra-xhigh-fresh-20261029t074303z version 0.1.0; unvalidated 70.1%
  46. 46 CADGenBench submission arche-industries_smith_20260828-220305: Smith version 0.1.0; unvalidated 69.3%
  47. 47 CADGenBench submission pzfreo_build123d-mcp-0-3-85-dev0-opus-5-xhigh-r_20260905-125604: build123d MCP 0.3.85.dev0 — Opus 5 xhigh — recognition-guided editing version 0.1.0; unvalidated 69%
  48. 48 CADGenBench submission rexl2018_vextor-vxl-agent-r4_20261105-013443: Vextor VXL agent (r4) version 0.1.0; unvalidated 68.8%
  49. 49 CADGenBench submission pzfreo_pzfreo-opus5-xhigh-mcp-drawing-evidence-_20260814-072949: pzfreo-opus5-xhigh-mcp-drawing-evidence-gen49-edit32 version 0.1.0; unvalidated 67.7%
  50. 50 CADGenBench submission andrii-pytel_daedalus-reader-agent-opus-high_20261023-074129: Daedalus - reader agent (opus, high) version 0.1.0; unvalidated 66.8%
  51. 51 CADGenBench submission cadse_v4-edits-full-run-v2-plus-9-built-edits-_20261112-145656: v4 edits: full run v2 plus 9 built edits and 18 unchanged editing inputs version 0.1.0; unvalidated 66.7%
  52. 52 CADGenBench submission mecado_astra-high-mecado-baseline-with-build123_20260921-202238: Astra high Mecado Baseline with Build123d version 0.1.0; unvalidated 66.2%
  53. 53 CADGenBench submission nik6_nik6-harness-c-v3_20260819-020220: nik6-harness-c-v3 version 0.1.0; unvalidated 65.8%
  54. 54 CADGenBench submission webmesh_webmesh-v4_20261105-043522: WebMesh v4 version 0.1.0; unvalidated 65.2%
  55. 55 CADGenBench submission nik6_nik6-harness-c-v2_20260818-031411: nik6-harness-c-v2 version 0.1.0; unvalidated 64.3%
  56. 56 CADGenBench submission nataliya-shakhovska_daedalus-a4h-opus55-medium-r2_20261112-150429: daedalus-a4h-opus55-medium-r2 version 0.1.0; unvalidated 64.2%
  57. 57 CADGenBench submission pzfreo_build123d-mcp-v0381-claude-opus-5-xhigh-_20260807-101147: build123d-mcp-v0381-claude-opus-5-xhigh-full-r6 version 0.1.0; validated 63.9%
  58. 58 CADGenBench submission modelcorp_baseline-astra-codex-low-v0_20260904-225835: baseline-astra-codex-low-v0 version 0.1.0; unvalidated 63.7%
  59. 59 CADGenBench submission saysolid-adapted-hub-llc_saysolid-gpt-6-1-sol-exact-dataset-nativ_20261025-071859: SaySolid gpt-6.1-sol exact-dataset-native-inputs visual-critic worker 682232c8535e version 0.1.0; unvalidated 63.6%
  60. 60 CADGenBench submission saysolid-adapted-hub-llc_saysolid-gpt-6-1-sol-exact-dataset-nativ_20261025-145423: SaySolid gpt-6.1-sol exact-dataset-native-inputs visual-critic worker 682232c8535e version 0.1.0; unvalidated 63.6%
  61. 61 CADGenBench submission nataliya-shakhovska_daedalus-a4h-opus55-medium-r1_20261112-150227: daedalus-a4h-opus55-medium-r1 version 0.1.0; unvalidated 63%
  62. 62 CADGenBench submission nataliya-shakhovska_daedalus-a4h-opus55-medium-r3_20261112-150542: daedalus-a4h-opus55-medium-r3 version 0.1.0; unvalidated 63%
  63. 63 CADGenBench submission mecado_astra-xhigh-mecado-baseline-with-build12_20260921-201510: Astra xhigh Mecado Baseline with Build123d version 0.1.0; unvalidated 63%
  64. 64 CADGenBench submission andrii-pytel_daedalus-phased-pipeline-opus-medium_20261007-144742: Daedalus - phased pipeline (opus, medium) version 0.1.0; unvalidated 62.9%
  65. 65 CADGenBench submission rexl2018_vextor-vxl-agent-engine-0030ca21-r3_20261103-142422: Vextor VXL agent (engine 0030ca21, r3) version 0.1.0; unvalidated 62.7%
  66. 66 CADGenBench submission pzfreo_opus5-xhigh-official-baseline-prompt-nom_20260811-034944: opus5-xhigh-official-baseline-prompt-nomcp-complete-r1 version 0.1.0; unvalidated 62.7%
  67. 67 CADGenBench submission andrii-pytel_daedalus-phased-pipeline-opus-high_20261023-105235: Daedalus - phased pipeline (opus, high) version 0.1.0; unvalidated 62.6%
  68. 68 CADGenBench submission andrii-pytel_daedalus-reader-agent-opus-medium_20261024-185917: Daedalus - reader agent (opus, medium) version 0.1.0; unvalidated 62.6%
  69. 69 CADGenBench submission andrii-pytel_daedalus-phased-pipeline-opus-medium-fin_20261018-191648: Daedalus - phased pipeline (opus, medium) - final r1 version 0.1.0; unvalidated 62.1%
  70. 70 CADGenBench submission cadse_baseline-v3-full-run-v2-27-editing-input_20261112-130649: baseline v3: full run v2 + 27 editing inputs unchanged (no-op floor), Opus xhigh, shift 0.7 % on generation only version 0.1.0; unvalidated 61.9%
  71. 71 CADGenBench submission saysolid-adapted-hub-llc_saysolid-gpt-6-astra-edits-gpt-5-6-sol-e_20260916-012742: SaySolid gpt-6-astra (edits gpt-5.6-sol) exact-dataset-native-inputs worker ce6aa3128893 version 0.1.0; unvalidated 61.5%
  72. 72 CADGenBench submission saysolid-adapted-hub-llc_saysolid-claude-opus-5-5-exact-dataset-n_20261013-180006: SaySolid claude-opus-5-5 exact-dataset-native-inputs worker d9fd87a7c343 version 0.1.0; unvalidated 61.3%
  73. 73 CADGenBench submission saysolid-adapted-hub-llc_saysolid-gpt-6-1-sol-exact-dataset-nativ_20260930-020419: SaySolid gpt-6.1-sol exact-dataset-native-inputs worker 672ab9a3732b version 0.1.0; unvalidated 61.2%
  74. 74 CADGenBench submission saysolid-adapted-hub-llc_saysolid-gpt-6-1-sol-exact-dataset-nativ_20261023-192958: SaySolid gpt-6.1-sol exact-dataset-native-inputs worker 682232c8535e version 0.1.0; unvalidated 61.1%
  75. 75 CADGenBench submission nik6_nik6-harness-c-v1_20260816-183610: nik6-harness-c-v1 version 0.1.0; unvalidated 61.1%
  76. 76 CADGenBench submission andrii-pytel_daedalus-reader-wholesheet-ablation-opus_20261024-230348: daedalus-reader-wholesheet-ablation-opus-medium version 0.1.0; unvalidated 60.1%
  77. 77 CADGenBench submission saysolid-adapted-hub-llc_saysolid-gpt-6-1-sol-exact-dataset-nativ_20261008-110521: SaySolid gpt-6.1-sol exact-dataset-native-inputs worker 04d40445ddc3 version 0.1.0; unvalidated 60%
  78. 78 CADGenBench submission saysolid-adapted-hub-llc_saysolid-gpt-6-1-sol-exact-dataset-nativ_20261104-222118: SaySolid gpt-6.1-sol exact-dataset-native-inputs worker 545fa00b8179 version 0.1.0; unvalidated 59.9%
  79. 79 CADGenBench submission andrii-pytel_daedalus-phased-pipeline-opus-medium_20261024-185836: Daedalus - phased pipeline (opus, medium) version 0.1.0; unvalidated 59.3%
  80. 80 CADGenBench submission matthew-lieb_cadi-generation-and-editing-2026-09-19_20260920-153059: CADI generation and editing, 2026-09-19 version 0.1.0; unvalidated 58.7%
  81. 81 CADGenBench submission pzfreo_build123d-mcp-0-3-84-dev0-gemini-3-8-fla_20260904-032010: build123d-mcp-0.3.84.dev0-gemini-3.8-flash-high-repair-first-complete81-r2 version 0.1.0; unvalidated 57.9%
  82. 82 CADGenBench submission rexl2018_vextor-vxl-agent-engine-4cd1e674-r2_20261102-163559: Vextor VXL agent (engine 4cd1e674, r2) version 0.1.0; unvalidated 57.5%
  83. 83 CADGenBench submission xueqinglin_openai-gpt-5-6-sol-claude-code-20260827-_20260827-063801: openai.gpt-5.6-sol_claude-code_20260827-114734 version 0.1.0; unvalidated 57.5%
  84. 84 CADGenBench submission nik6_nik6-cadgenbench-v1_20260808-223843: nik6-cadgenbench-v1 version 0.1.0; unvalidated 57.4%
  85. 85 CADGenBench submission nik6_nik6-cadgenbench-v1_20260808-231147: nik6-cadgenbench-v1 version 0.1.0; unvalidated 57.4%
  86. 86 CADGenBench submission rexl2018_vextor-vxl-agent-engine-4cd1e674_20261102-150618: Vextor VXL agent (engine 4cd1e674) version 0.1.0; unvalidated 57.3%
  87. 87 CADGenBench submission nik6_nik6-harness-v8-v1_20260831-043302: nik6-harness-v8-v1 version 0.1.0; unvalidated 56.9%
  88. 88 CADGenBench submission pzfreo_build123d-mcp-0-3-84-dev0-gemini-3-8-fla_20260904-034650: build123d-mcp-0.3.84.dev0-gemini-3.8-flash-high-recognition-execution-gen-dev388-complete81-r2 version 0.1.0; unvalidated 56.6%
  89. 89 CADGenBench submission pzfreo_build123d-mcp-0-3-84-dev388-gemini-3-8-f_20260903-075326: build123d-mcp-0.3.84.dev388-gemini-3.8-flash-high version 0.1.0; unvalidated 56.1%
  90. 90 CADGenBench submission pzfreo_build123d-mcp-0-3-84-dev0-gemini-3-8-fla_20260903-141226: build123d-mcp-0.3.84.dev0-gemini-3.8-flash-high-recognition-forced-editing-gen-dev388-complete81-r1 version 0.1.0; unvalidated 55.9%
  91. 91 CADGenBench submission xueqinglin_claude-opus-5-claude-code-20260825-17400_20260825-095149: claude-opus-5_claude-code_20260825-174002 version 0.1.0; unvalidated 55.8%
  92. 92 CADGenBench submission experiment_experiment_20260923-134635: Experiment version 0.1.0; unvalidated 55.7%
  93. 93 CADGenBench submission saysolid-adapted-hub-llc_saysolid-gpt-6-astra-exact-dataset-nativ_20260905-170835: SaySolid gpt-6-astra exact-dataset-native-inputs worker f4566f7b5661 version 0.1.0; unvalidated 55%
  94. 94 CADGenBench submission b-rat_agent-cad-harness-claude-fable-5-1-gen49_20261012-002331: agent-cad harness / Claude Fable 5.1 (gen49 + edit32) version 0.1.0; unvalidated 54.9%
  95. 95 CADGenBench submission andrii-pytel_daedalus-single-react-agent-opus-medium_20261004-190209: Daedalus - single ReAct agent (opus, medium) version 0.1.0; unvalidated 54.4%
  96. 96 CADGenBench submission xueqinglin_openai-gpt-5-6-sol-baseline-20260826-193_20260826-115643: openai.gpt-5.6-sol_baseline_20260826-193928 version 0.1.0; unvalidated 53.9%
  97. 97 CADGenBench submission cadgenbench-2d-to-3d_gpt-6-1-sol-agentic-baseline_20261012-111954: gpt-6.1-sol agentic baseline version 0.1.0; unvalidated 53.7%
  98. 98 CADGenBench submission andrii-pytel_daedalus-single-react-agent-opus-medium-_20261017-111238: Daedalus - single ReAct agent (opus, medium) - run 3 version 0.1.0; unvalidated 53.3%
  99. 99 CADGenBench submission pzfreo_gpt-5-6-sol-xhigh-floor-chain-v0379_20260717-045810: gpt-5.6-sol-xhigh-floor-chain-v0379 version 0.1.0; validated 53.2%
  100. 100 CADGenBench submission andrii-pytel_daedalus-single-react-agent-opus-medium-_20261017-105639: Daedalus - single ReAct agent (opus, medium) - run 2 version 0.1.0; unvalidated 53%
  101. 101 CADGenBench submission mecado_grok-4-7-xhigh-mecado-baseline-with-buil_20260921-210958: Grok 4.7 xhigh Mecado Baseline with Build123d version 0.1.0; unvalidated 52.1%
  102. 102 CADGenBench submission origogk_origogk-r24-convex-faces-remodels-108-11_20261019-142941: OrigoGK r24 convex faces + remodels 108 112 116 118 119 132 134 138 145 version 0.1.0; unvalidated 51.7%
  103. 103 CADGenBench submission cadse_brief-v7-full-run-49-generation-parts-op_20261112-180052: brief v7 full run, 49 generation parts, Opus builder version 0.1.0; unvalidated 51.1%
  104. 104 CADGenBench submission pzfreo_build123d-mcp-0-3-83-gemini-flash-3-7_20260902-022750: build123d-mcp-0.3.83-gemini-flash-3.7 version 0.1.0; unvalidated 50.8%
  105. 105 CADGenBench submission satvik-adyanthaya_archie-in-forge_20260711-184330: Archie in Forge version 0.1.0; validated 50.7%
  106. 106 CADGenBench submission anonymous_anonymous-agent_20260914-123111: Anonymous agent version 0.1.0; unvalidated 50.6%
  107. 107 CADGenBench submission anon-12345_generation-editing_20261015-144308: generation-editing version 0.1.0; unvalidated 50.4%
  108. 108 CADGenBench submission experiment_experiment_20260822-234139: Experiment version 0.1.0; unvalidated 49.8%
  109. 109 CADGenBench submission modelcorp_baseline-astra-codex-medium-single-sessi_20260904-202625: baseline_astra_codex_medium_single_session version 0.1.0; unvalidated 49.8%
  110. 110 CADGenBench submission modelcorp_baseline-astra-codex-sequential-pass_20260904-201609: baseline_astra_codex_sequential_pass version 0.1.0; unvalidated 49.8%
  111. 111 CADGenBench submission anonymous_anon-gen-1788896800-17b078_20260908-194644: anon-gen-1788896800-17b078 version 0.1.0; unvalidated 49.7%
  112. 112 CADGenBench submission mecado_grok-4-7-high-mecado-baseline-with-build_20260921-211028: Grok 4.7 high Mecado Baseline with Build123d version 0.1.0; unvalidated 49.6%
  113. 113 CADGenBench submission cadse_full-run-v2-49-parts-all-opus-xhigh-full_20261112-123301: full run v2: 49 parts, all Opus xhigh, full brief + principles + hole rules v2, shift 0.7 % version 0.1.0; unvalidated 49.5%
  114. 114 CADGenBench submission anonymous_anon-gen-1789061429-b7ed34_20260910-175227: anon-gen-1789061429-b7ed34 version 0.1.0; unvalidated 49.5%
  115. 115 CADGenBench submission experiment_experiment_20260913-202641: Experiment version 0.1.0; unvalidated 49.4%
  116. 116 CADGenBench submission xueqinglin_baseline-gpt-5-6-sol-build123d_20260819-035800: baseline_gpt-5.6-sol_build123d version 0.1.0; unvalidated 49.4%
  117. 117 CADGenBench submission xueqinglin_baseline-gpt-5-6-sol-build123d_20260819-062918: baseline_gpt-5.6-sol_build123d version 0.1.0; unvalidated 49.4%
  118. 118 CADGenBench submission anonymous_test-submission-format_20260904-192600: test_submission_format version 0.1.0; unvalidated 49%
  119. 119 CADGenBench submission cadse_full-run-v1-49-parts-full-brief-principl_20261112-115103: full run v1: 49 parts, full brief + principles + hole rules v2, Opus builder (xhigh for 9 fixtures and 21 others), shift 0.7 % version 0.1.0; unvalidated 48.6%
  120. 120 CADGenBench submission makinarocks_drawx-2d3d-v4-gpt-6-astra_20261025-100833: drawx 2d3d v4 (gpt-6-astra) version 0.1.0; unvalidated 48.5%
  121. 121 CADGenBench submission w1ne_kernelcad-dev-refresh-20261026_20261026-192821: kernelcad-dev-refresh-20261026 version 0.1.0; unvalidated 48.4%
  122. 122 CADGenBench submission anonymous_anonymous-agent_20260914-095345: Anonymous agent version 0.1.0; unvalidated 48.4%
  123. 123 CADGenBench submission anonymous_deskwright-gpt-5-5-xhigh-native-inline_20260830-182813: DeskWright GPT-5.5 xhigh native-inline version 0.1.0; unvalidated 47.9%
  124. 124 CADGenBench submission anon-12345_generation-editing_20261015-002847: generation-editing version 0.1.0; unvalidated 47.6%
  125. 125 CADGenBench submission w1ne_kernelcad-7e9082ab-gpt-5-6-sol-xhigh_20261019-105100: kernelcad-7e9082ab-gpt-5.6-sol-xhigh version 0.1.0; unvalidated 47.5%
  126. 126 CADGenBench submission saysolid-adapted-hub-llc_saysolid-gpt-6-astra-exact-dataset-nativ_20260914-192424: SaySolid gpt-6-astra exact-dataset-native-inputs generation-arm-only worker 08f43e775f98 version 0.1.0; unvalidated 47.4%
  127. 127 CADGenBench submission origogk_origogk-r23-simplified-export-remodels-1_20261004-210724: OrigoGK r23 simplified export + remodels 112 118 119 134 version 0.1.0; unvalidated 47%
  128. 128 CADGenBench submission anon-12345_generation-editing_20261013-140852: generation-editing version 0.1.0; unvalidated 46.8%
  129. 129 CADGenBench submission xueqinglin_glm-5-3-flash-claude-code-20260908-22435_20260909-022803: glm-5.3-flash_claude-code_20260908-224350 version 0.1.0; unvalidated 46.7%
  130. 130 CADGenBench submission rouan_cadrs-claude-opus-5-5-mcp-hand-driven-r2_20261010-090115: cadrs + Claude Opus 5.5 (MCP, hand-driven) r2 version 0.1.0; unvalidated 46.7%
  131. 131 CADGenBench submission xueqinglin_claude-opus-5-baseline-20260820-194627_20260820-115133: claude-opus-5_baseline_20260820-194627 version 0.1.0; unvalidated 46.3%
  132. 132 CADGenBench submission pzfreo_gpt55-v0368-xhigh-full_20260706-050450: gpt55-v0368-xhigh-full version 0.1.0; unvalidated 46.1%
  133. 133 CADGenBench submission pzfreo_gpt55-v0366-xhigh-full-vtkfix_20260704-200116: gpt55-v0366-xhigh-full-vtkfix version 0.1.0; unvalidated 46.1%
  134. 134 CADGenBench submission pzfreo_pzfreo-gpt55-v0376-xhigh-full_20260709-181849: pzfreo-gpt55-v0376-xhigh-full version 0.1.0; unvalidated 46%
  135. 135 CADGenBench submission makinarocks_drawx-2d3d-v4-gpt-6-1-sol_20261025-051216: drawx 2d3d v4 (gpt-6.1-sol) version 0.1.0; unvalidated 45.8%
  136. 136 CADGenBench submission pzfreo_gpt-5-5-build123d-mcp-0-3-59-xhigh-r5_20260627-141619: gpt-5.5-build123d-mcp-0.3.59-xhigh-r5 version 0.1.0; validated 45.7%
  137. 137 CADGenBench submission xueqinglin_openai-gpt-5-6-sol-claude-code-20260825-_20260825-055902: openai.gpt-5.6-sol_claude-code_20260825-114538 version 0.1.0; unvalidated 45.5%
  138. 138 CADGenBench submission andrii-pytel_daedalus-one-shot-script-opus-medium-run_20261017-111400: Daedalus - one-shot script (opus, medium) - run 3 version 0.1.0; unvalidated 45.4%
  139. 139 CADGenBench submission arche_smith_20260711-010918: Smith version 0.1.0; unvalidated 45.3%
  140. 140 CADGenBench submission pzfreo_gpt-5-5-b123d-mcp-0-3-59-xhigh-full-p1_20260701-223602: gpt-5.5-b123d-mcp-0.3.59-xhigh-full-P1 version 0.1.0; unvalidated 45.2%
  141. 141 Claude Fable 5 45.1%
  142. 142 CADGenBench submission jspark_gpt-5-6-sol-build123d-loop-2_20260824-032415: gpt-5.6-sol_build123d_loop_2 version 0.1.0; unvalidated 45%
  143. 143 CADGenBench submission anon-12345_generation-editing_20261003-134956: generation-editing version 0.1.0; unvalidated 45%
  144. 144 CADGenBench submission james-dillard_claude-opus-5-5-candidate-p-pi-harness-s_20261002-094853: Claude Opus 5.5 Candidate P (Pi harness, standard help, 2026-10-01) version 0.1.0; unvalidated 44.7%
  145. 145 CADGenBench submission pzfreo_gpt-5-5-build123d-mcp-0-3-57-xhigh_20260624-051501: gpt-5.5-build123d-mcp-0.3.57-xhigh version 0.1.0; unvalidated 44.5%
  146. 146 CADGenBench submission saysolid-adapted-hub-llc_saysolid-gpt-5-6-sol-exact-dataset-nativ_20260829-132038: SaySolid gpt-5.6-sol exact-dataset-native-inputs worker 4af68790c698 version 0.1.0; unvalidated 44.5%
  147. 147 CADGenBench submission xueqinglin_kimi-k3-claude-code-20260907-214127_20260908-125546: kimi-k3_claude-code_20260907-214127 version 0.1.0; unvalidated 44.4%
  148. 148 CADGenBench submission mecado_grok-4-6-high-mecado-baseline-with-build_20260813-210045: Grok 4.6 high Mecado Baseline with Build123d version 0.1.0; validated 44.4%
  149. 149 CADGenBench submission pzfreo_gpt55-v0364-xhigh-full-verifyspec_20260704-055230: gpt55-v0364-xhigh-full-verifyspec version 0.1.0; unvalidated 43.9%
  150. 150 CADGenBench submission origogk_origogk-r22-edit-operators-208-217-218-2_20261004-051610: OrigoGK r22 edit operators 208 217 218 224 248 version 0.1.0; unvalidated 43.8%
  151. 151 CADGenBench submission daanderson_fs-mcp-fable-5-minimal-harness_20260706-113645: FS MCP - Fable 5 - Minimal Harness version 0.1.0; unvalidated 43.6%
  152. 152 CADGenBench submission xueqinglin_dashscope-qwen3-8-max-baseline-20260820-_20260820-075059: dashscope.qwen3.8-max_baseline_20260820-152330 version 0.1.0; unvalidated 43.6%
  153. 153 CADGenBench submission andrii-pytel_daedalus-one-shot-script-opus-medium_20261004-184853: Daedalus - one-shot script (opus, medium) version 0.1.0; unvalidated 43.6%
  154. 154 CADGenBench submission test-submission_browser-based-cad-agent-full-81-sample-r_20260904-223403: Browser-based CAD agent — full 81-sample run version 0.1.0; unvalidated 43.6%
  155. 155 CADGenBench submission mecado_claude-opus-5-max-mecado-baseline-with-b_20260813-223230: Claude Opus 5 max Mecado Baseline with Build123d version 0.1.0; validated 43.2%
  156. 156 CADGenBench submission xueqinglin_dashscope-qwen3-8-max-claude-code-202608_20260826-113028: dashscope.qwen3.8-max_claude-code_20260826-192133 version 0.1.0; unvalidated 43.2%
  157. 157 CADGenBench submission xueqinglin_openai-gpt-5-6-sol-baseline-20260820-184_20260820-112107: openai.gpt-5.6-sol_baseline_20260820-184227 version 0.1.0; unvalidated 43.1%
  158. 158 CADGenBench submission makinarocks_drawx-2d3d-v53-gpt-6-1-terra_20261027-061524: drawx 2d3d v53 (gpt-6.1-terra) version 0.1.0; unvalidated 43%
  159. 159 CADGenBench submission jspark_gpt-5-6-sol-build123d_20260717-074106: gpt-5.6-sol build123d version 0.1.0; unvalidated 43%
  160. 160 CADGenBench submission paul-fremantle-pzfreo_build123d-mcp-claude-opus-4-8-full-81-fi_20260621-073422: build123d-mcp + Claude Opus 4.8 (full, 81 fixtures) version 0.1.0; validated 42.8%
  161. 161 CADGenBench submission saysolid-adapted-hub-llc_saysolid-gpt-5-6-sol-exact-dataset-nativ_20260829-225405: SaySolid gpt-5.6-sol exact-dataset-native-inputs worker 4af68790c698 version 0.1.0; unvalidated 42.7%
  162. 162 CADGenBench submission pzfreo_claude-opus-4-8-build123d-mcp-0-3-56_20260622-220357: claude-opus-4.8-build123d-mcp-0.3.56 version 0.1.0; unvalidated 42.7%
  163. 163 CADGenBench submission pzfreo_pzfreo_20260622-205211: pzfreo version 0.1.0; unvalidated 42.7%
  164. 164 CADGenBench submission saysolid-adapted-hub-llc_saysolid-gpt-5-6-sol-exact-dataset-nativ_20260902-143854: SaySolid gpt-5.6-sol exact-dataset-native-inputs worker 364c948f664d version 0.1.0; unvalidated 42.5%
  165. 165 CADGenBench submission rouan_cadrs-claude-opus-5-5-mcp-hand-driven_20261010-040826: cadrs + Claude Opus 5.5 (MCP, hand-driven) version 0.1.0; unvalidated 42.5%
  166. 166 CADGenBench submission mecado_grok-4-6-xhigh-mecado-baseline-with-buil_20260813-215410: Grok 4.6 xhigh Mecado Baseline with Build123d version 0.1.0; validated 42.4%
  167. 167 CADGenBench submission saysolid-adapted-hub-llc_saysolid-gpt-5-6-sol-exact-dataset-nativ_20260829-181641: SaySolid gpt-5.6-sol exact-dataset-native-inputs worker 4af68790c698 version 0.1.0; unvalidated 42.3%
  168. 168 CADGenBench submission saysolid-adapted-hub-llc_saysolid-gpt-5-6-sol-exact-dataset-nativ_20260829-080934: SaySolid gpt-5.6-sol exact-dataset-native-inputs worker 464ef83f8531 version 0.1.0; unvalidated 42.3%
  169. 169 CADGenBench submission pzfreo_gpt-5-6-sol-medium-mcp-0-3-78_20260711-055408: gpt-5.6-sol-medium-mcp-0.3.78 version 0.1.0; unvalidated 42.1%
  170. 170 CADGenBench submission andrii-pytel_daedalus-one-shot-script-opus-medium-run_20261017-111318: Daedalus - one-shot script (opus, medium) - run 2 version 0.1.0; unvalidated 42%
  171. 171 CADGenBench submission xueqinglin_openai-gpt-5-6-sol-baseline-20260825-111_20260825-033327: openai.gpt-5.6-sol_baseline_20260825-111524 version 0.1.0; unvalidated 41.5%
  172. 172 CADGenBench submission mecado_gpt-5-6-sol-xhigh-mecado-baseline-with-b_20260813-233018: GPT-5.6 Sol xhigh Mecado Baseline with Build123d version 0.1.0; validated 41.2%
  173. 173 CADGenBench submission pzfreo_gpt-5-5-build123d-mcp-0-3-56-v2_20260623-161750: gpt-5.5-build123d-mcp-0.3.56-v2 version 0.1.0; validated 41.1%
  174. 174 CADGenBench submission pzfreo_gpt-5-5-build123d-mcp-0-3-59-medium-r2_20260627-143151: gpt-5.5-build123d-mcp-0.3.59-medium-r2 version 0.1.0; unvalidated 41.1%
  175. 175 CADGenBench submission michaelr27_gpt-5-6-sol-hf-baseline-with-build123d_20260713-183956: GPT-5.6 Sol HF Baseline with Build123d version 0.1.0; validated 41.1%
  176. 176 CADGenBench submission saysolid-adapted-hub-llc_saysolid-gpt-5-6-sol-exact-dataset-nativ_20260902-063145: SaySolid gpt-5.6-sol exact-dataset-native-inputs worker 364c948f664d version 0.1.0; unvalidated 40.8%
  177. 177 CADGenBench submission anonymous_anon-gen-1788841910-f09d41_20260908-043152: anon-gen-1788841910-f09d41 version 0.1.0; unvalidated 40.8%
  178. 178 CADGenBench submission bolev-mikhail_b2c-opus5-finish-v2-gen49_20260916-113951: b2c-opus5-finish-v2-gen49 version 0.1.0; unvalidated 40.7%
  179. 179 CADGenBench submission dani2l_build123d-mcp-0-3-91-sonnet-5-5_20261029-043937: build123d-mcp-0.3.91-sonnet-5.5 version 0.1.0; unvalidated 40.6%
  180. 180 CADGenBench submission anon-12345_generation_20260930-134942: generation version 0.1.0; unvalidated 40.5%
  181. 181 CADGenBench submission saysolid-adapted-hub-llc_saysolid-gpt-5-6-sol-exact-dataset-nativ_20260902-201006: SaySolid gpt-5.6-sol exact-dataset-native-inputs worker 364c948f664d version 0.1.0; unvalidated 40.2%
  182. 182 CADGenBench submission origogk_origogk-r21-pinched-sliver-repair-240_20261001-033654: OrigoGK r21 pinched sliver repair 240 version 0.1.0; unvalidated 40.2%
  183. 183 CADGenBench submission jspark_gpt-5-6-sol-cadquery-max-iter5_20260712-145235: gpt-5.6-sol cadquery max-iter5 version 0.1.0; unvalidated 39.8%
  184. 184 CADGenBench submission origogk_origogk-r20-face-extrusions-209-211-240_20261001-021200: OrigoGK r20 face extrusions 209 211 240 version 0.1.0; unvalidated 39.5%
  185. 185 CADGenBench submission anonymous_anon-gen-1787944336-7ffd_20260828-191217: anon-gen-1787944336-7ffd version 0.1.0; unvalidated 39.4%
  186. 186 CADGenBench submission anonymous_anon-gen-1787928380-e027_20260828-144621: anon-gen-1787928380-e027 version 0.1.0; unvalidated 39.4%
  187. 187 CADGenBench submission anon-12345_generation_20260929-041603: generation version 0.1.0; unvalidated 39.1%
  188. 188 CADGenBench submission unifyh_opus-48-toy-plugin-run4_20260709-031252: opus-48-toy-plugin-run4 version 0.1.0; unvalidated 38.8%
  189. 189 GPT-5.5 Pro 38.7%
  190. 190 CADGenBench submission jselstad_opus-4-8-claude-code-text-to-cad-skill_20260618-075019: Opus 4.8 — Claude Code + text-to-cad skill version 0.1.0; validated 38.7%
  191. 191 CADGenBench submission anonymous_anon-gen-1787893554-7a60_20260828-050555: anon-gen-1787893554-7a60 version 0.1.0; unvalidated 38.2%
  192. 192 CADGenBench submission origogk_origogk-r19-hole-removal-205_20260930-125014: OrigoGK r19 hole removal 205 version 0.1.0; unvalidated 37.9%
  193. 193 CADGenBench submission arche_smith_20260710-221438: Smith version 0.1.0; unvalidated 37.8%
  194. 194 CADGenBench submission anonymous_anon-gen-1787884326-48c4_20260828-023207: anon-gen-1787884326-48c4 version 0.1.0; unvalidated 37.6%
  195. 195 CADGenBench submission anonymous_anon-gen-1787868852-149a_20260827-221413: anon-gen-1787868852-149a version 0.1.0; unvalidated 37.5%
  196. 196 CADGenBench submission mecado_grok-4-5-high-mecado-baseline-with-build_20260813-203342: Grok 4.5 high Mecado Baseline with Build123d version 0.1.0; unvalidated 37%
  197. 197 Claude Opus 4.7 36.9%
  198. 198 CADGenBench submission min-liu_chamfer-cad-agent-from-smartai_20260705-213856: Chamfer-CAD agent from SmartAI version 0.1.0; unvalidated 36.8%
  199. 199 CADGenBench submission test_test-submission_20260702-031247: test submission version 0.1.0; unvalidated 36.7%
  200. 200 CADGenBench submission bolev-mikhail_b2c-opus5-tools-gen49_20260910-122220: b2c-opus5-tools-gen49 version 0.1.0; unvalidated 36.7%
  201. 201 CADGenBench submission origogk_origogk-r15-sliver-repair-250_20260930-105932: OrigoGK r15 sliver repair 250 version 0.1.0; unvalidated 36.6%
  202. 202 CADGenBench submission jselstad_opus-4-8-claude-code-build123d-mcp_20260618-080918: Opus 4.8 — Claude Code + build123d-mcp version 0.1.0; unvalidated 36.4%
  203. 203 CADGenBench submission anon-12345_generation_20260928-152617: generation version 0.1.0; unvalidated 36.4%
  204. 204 GPT-5.5 36%
  205. 205 CADGenBench submission unifyh_opus-48-toy-plugin-run3_20260703-060749: opus-48-toy-plugin-run3 version 0.1.0; unvalidated 35.9%
  206. 206 CADGenBench submission unifyh_opus-48-toy-plugin-run2_20260703-024748: opus-48-toy-plugin-run2 version 0.1.0; unvalidated 35.9%
  207. 207 CADGenBench submission chow_20260902-114129-muse-spark-full_20260903-154026: 20260902_114129_muse-spark_full version 0.1.0; unvalidated 35.8%
  208. 208 CADGenBench submission anonymous_anon-gen-1787797492-bb9e_20260827-022453: anon-gen-1787797492-bb9e version 0.1.0; unvalidated 35.8%
  209. 209 CADGenBench submission origogk_origogk-r14-face-offsets-231-250_20260930-100641: OrigoGK r14 face offsets 231 250 version 0.1.0; unvalidated 35.7%
  210. 210 CADGenBench submission nataliya-shakhovska_daedalus-a4h-nogate-opus55-medium-r1_20261111-115811: daedalus-a4h-nogate-opus55-medium-r1 version 0.1.0; unvalidated 35.3%
  211. 211 CADGenBench submission nataliya-shakhovska_daedalus-a4h-nogate-opus55-medium-r3_20261112-145445: daedalus-a4h-nogate-opus55-medium-r3 version 0.1.0; unvalidated 35.2%
  212. 212 CADGenBench submission nrocketmann_glm-5-3-max-agentic-cad-zcode-subagents-_20260903-065136: GLM-5.3-Max agentic CAD (ZCode subagents, build123d) version 0.1.0; unvalidated 35.1%
  213. 213 CADGenBench submission jselstad_opus-4-8-claude-code-basic-no-mcp-skill_20260618-071847: Opus 4.8 — Claude Code (basic, no MCP/skill) version 0.1.0; unvalidated 34.9%
  214. 214 CADGenBench submission reckless-lampshade-230826_gpt-5-6-combined-best-generation_20260823-174609: gpt 5.6 combined best generation version 0.1.0; unvalidated 34.6%
  215. 215 CADGenBench submission nataliya-shakhovska_daedalus-a4h-notable-opus55-medium-r1_20261111-123643: daedalus-a4h-notable-opus55-medium-r1 version 0.1.0; unvalidated 34.6%
  216. 216 Claude Opus 4.8 34.5%
  217. 217 CADGenBench submission origogk_origogk-r13-partial-238-thickness-edit_20260930-050126: OrigoGK r13 partial 238 thickness edit version 0.1.0; unvalidated 34.5%
  218. 218 CADGenBench submission nataliya-shakhovska_daedalus-a4h-nogate-opus55-medium-r2_20261112-144806: daedalus-a4h-nogate-opus55-medium-r2 version 0.1.0; unvalidated 34.4%
  219. 219 CADGenBench submission shashwatsaxena136_opus-4-8-build123d-baseline-full-81_20260615-171912: Opus 4.8 build123d baseline (full 81) version 0.1.0; unvalidated 34.3%
  220. 220 CADGenBench submission pzfreo_build123d-mcp-0-3-90-gemini-4-argon-high_20261022-124342: build123d-mcp-0.3.90-gemini-4-argon-high version 0.1.0; unvalidated 34.2%
  221. 221 CADGenBench submission james-dillard_gpt-6-luna-candidate-n-pi-harness-five-s_20261002-094803: GPT-6 Luna Candidate N (Pi harness, five-stage workflow, 2026-10-01) version 0.1.0; unvalidated 34%
  222. 222 CADGenBench submission nataliya-shakhovska_daedalus-a4h-notable-opus55-medium-r3_20261112-145541: daedalus-a4h-notable-opus55-medium-r3 version 0.1.0; unvalidated 34%
  223. 223 CADGenBench submission origogk_origogk-r12-remove-faces-edit-128-closed_20260930-033916: OrigoGK r12 remove-faces edit + 128 closed slots version 0.1.0; unvalidated 34%
  224. 224 CADGenBench submission jselstad_opus-4-8-claude-code-build123d-mcp_20260617-144101: Opus 4.8 — Claude Code + build123d-mcp version 0.1.0; unvalidated 33.9%
  225. 225 CADGenBench submission gpt-code_glm-5-3-flash-cadgenbench-baseline_20260831-100955: GLM-5.3-Flash CADGenBench baseline version 0.1.0; unvalidated 33.9%
  226. 226 CADGenBench submission hermes-agent_cadqueryskills-hermes-gpt-5-6-luna_20260921-191629: CadQuerySkills + Hermes + GPT-5.6-Luna version 0.1.0; unvalidated 33.9%
  227. 227 CADGenBench submission nataliya-shakhovska_daedalus-a4h-notable-opus55-medium-r2_20261112-145255: daedalus-a4h-notable-opus55-medium-r2 version 0.1.0; unvalidated 33.7%
  228. 228 CADGenBench submission fuhao_opencode-qwen3-8-max-2d-to-3d-plugin-0-7_20261108-070837: opencode + qwen3.8-max · 2d-to-3d plugin 0.7.7.2-dev3 version 0.1.0; unvalidated 33.5%
  229. 229 CADGenBench submission fuhao_opencode-qwen3-8-max-baseline-no-plugin_20261108-065450: opencode + qwen3.8-max · baseline (no plugin) version 0.1.0; unvalidated 33%
  230. 230 CADGenBench submission anonymous_anon-gen-1787778946-d6ad_20260826-211548: anon-gen-1787778946-d6ad version 0.1.0; unvalidated 32.9%
  231. 231 CADGenBench submission james-dillard_gpt-6-luna-candidate-m-pi-harness-contro_20261002-094716: GPT-6 Luna Candidate M (Pi harness, control help, 2026-10-01) version 0.1.0; unvalidated 32.9%
  232. 232 CADGenBench submission james-dillard_gpt-5-6-sol-candidate-g-pi-harness-2026-_20260831-091037: GPT-5.6 Sol Candidate G (Pi harness, 2026-08-28) version 0.1.0; unvalidated 32.9%
  233. 233 CADGenBench submission shean-rahman_kinth-cadgenbench-full-gpt-5-5-retry-3_20260630-181939: Kinth CADGenBench full gpt-5.5 retry 3 version 0.1.0; unvalidated 32.8%
  234. 234 CADGenBench submission origogk_origogk-r10-sparse-first-voxel-fallback_20260930-011452: OrigoGK r10 sparse-first voxel-fallback version 0.1.0; unvalidated 32.8%
  235. 235 CADGenBench submission james-dillard_gpt-5-6-sol-candidate-f-pi-harness-2026-_20260831-091039: GPT-5.6 Sol Candidate F (Pi harness, 2026-08-28) version 0.1.0; unvalidated 32.7%
  236. 236 CADGenBench submission origogk_origogk-r11-128-drawn-diameter-source_20260930-015114: OrigoGK r11 128 drawn-diameter source version 0.1.0; unvalidated 32.6%
  237. 237 CADGenBench submission james-dillard_gpt-5-6-sol-candidate-i-pi-harness-2026-_20260901-211012: GPT-5.6 Sol Candidate I (Pi harness, 2026-09-01) version 0.1.0; unvalidated 32.3%
  238. 238 CADGenBench submission origogk_origogk-r9-voxel-first-sliver-free_20260929-235952: OrigoGK r9 voxel-first sliver-free version 0.1.0; unvalidated 32.2%
  239. 239 CADGenBench submission jselstad_opus-4-8-claude-code-basic-no-mcp-skill_20260617-141618: Opus 4.8 — Claude Code (basic, no MCP/skill) version 0.1.0; unvalidated 32.2%
  240. 240 CADGenBench submission anon-120824_gpt-5-6_20260812-043905: gpt 5.6 version 0.1.0; unvalidated 31.6%
  241. 241 CADGenBench submission origogk_origogk-r7-reviewed-sources_20260929-233435: OrigoGK r7 reviewed-sources version 0.1.0; unvalidated 31.2%
  242. 242 CADGenBench submission origogk_origogk-r8-voxel-first_20260929-234724: OrigoGK r8 voxel-first version 0.1.0; unvalidated 31.1%
  243. 243 Gemini 3.1 Pro 31.1%
  244. 244 Claude Opus 4.6 30.9%
  245. 245 CADGenBench submission rakshit-dwivedi_proxima_20260903-035049: Proxima version 0.1.0; unvalidated 30.8%
  246. 246 CADGenBench submission nataliya-shakhovska_daedalus-a4h-whole-opus55-medium-r2_20261112-150703: daedalus-a4h-whole-opus55-medium-r2 version 0.1.0; unvalidated 30.7%
  247. 247 CADGenBench submission mliu_chamfer-cad-harness-0-1-1_20260707-033749: chamfer-cad-harness-0.1.1 version 0.1.0; unvalidated 30.5%
  248. 248 CADGenBench submission brambling_brambling_20260909-045047: brambling version 0.1.0; unvalidated 30.5%
  249. 249 CADGenBench submission anon-233107_eval-b12_20260912-051712: eval-b12 version 0.1.0; unvalidated 30.4%
  250. 250 CADGenBench submission saysolid-adapted-hub-llc_saysolid-gpt-5-6-luna-exact-dataset-nati_20260826-080728: SaySolid gpt-5.6-luna exact-dataset-native-inputs worker 41bd4d911831 version 0.1.0; unvalidated 30.2%
  251. 251 CADGenBench submission tharun-arety_cadrig-alpha_20260917-211434: CADRIG Alpha version 0.1.0; unvalidated 30%
  252. 252 CADGenBench submission cadsmith42_fable-5-1-agentic-editing-v2_20260913-185705: fable-5-1-agentic-editing-v2 version 0.1.0; unvalidated 30%
  253. 253 CADGenBench submission nataliya-shakhovska_daedalus-a4h-whole-opus55-medium-r3_20261112-150821: daedalus-a4h-whole-opus55-medium-r3 version 0.1.0; unvalidated 30%
  254. 254 CADGenBench submission anonymous_anon-edit-1787880475-69c8_20260828-012758: anon-edit-1787880475-69c8 version 0.1.0; unvalidated 29.9%
  255. 255 CADGenBench submission xueqinglin_dashscope-qwen3-8-max-claude-code-202608_20260825-110841: dashscope.qwen3.8-max_claude-code_20260825-190219 version 0.1.0; unvalidated 29.8%
  256. 256 CADGenBench submission nataliya-shakhovska_daedalus-a4h-whole-opus55-medium-r1_20261111-153840: daedalus-a4h-whole-opus55-medium-r1 version 0.1.0; unvalidated 29.8%
  257. 257 CADGenBench submission tomuiv_mad-deepseek-v4-1-flash-baseline_20261003-120717: MAD DeepSeek-V4.1-Flash baseline version 0.1.0; unvalidated 29.7%
  258. 258 CADGenBench submission phi-linh_cad-gen-v4_20260817-150126: cad-gen v4 version 0.1.0; unvalidated 29.7%
  259. 259 CADGenBench submission saysolid-adapted-hub-llc_saysolid-gpt-5-6-sol-exact-dataset-nativ_20260826-002817: SaySolid gpt-5.6-sol exact-dataset-native-inputs worker 41bd4d911831 version 0.1.0; unvalidated 29.7%
  260. 260 CADGenBench submission pzfreo_gpt-5-5-build123d-mcp-0-3-56-partial61of_20260623-111130: gpt-5.5-build123d-mcp-0.3.56-partial61of81 version 0.1.0; unvalidated 29.6%
  261. 261 CADGenBench submission origogk_origogk-r6-source-fix-edge-budget_20260929-170942: OrigoGK r6 source-fix edge-budget version 0.1.0; unvalidated 29.6%
  262. 262 CADGenBench submission pimbs_pimbsv1_20260901-191627: Pimbsv1 version 0.1.0; unvalidated 29.6%
  263. 263 CADGenBench submission anonymous_anon-edit-1787868057-f965_20260827-220059: anon-edit-1787868057-f965 version 0.1.0; unvalidated 29.5%
  264. 264 CADGenBench submission feral-teapot-230826_gpt-5-6_20260823-154940: gpt 5.6 version 0.1.0; unvalidated 29.4%
  265. 265 CADGenBench submission origogk_origogk-full-denominator-automatic-run-2_20260927-125419: OrigoGK full denominator automatic run 20260927 version 0.1.0; unvalidated 29.4%
  266. 266 CADGenBench submission anonymous_o-a1-1-f_20261021-142015: O-A1-1_f version 0.1.0; unvalidated 29.2%
  267. 267 CADGenBench submission anon-224918_sweep-g_20260911-054807: sweep-g version 0.1.0; unvalidated 28.9%
  268. 268 CADGenBench submission andrii-pytel_daedalus-single-react-agent-opus-medium_20261003-215209: Daedalus - single ReAct agent (opus, medium) version 0.1.0; unvalidated 28.7%
  269. 269 CADGenBench submission anonymous_anon-edit-1787797485-f5ff_20260827-022447: anon-edit-1787797485-f5ff version 0.1.0; unvalidated 28.7%
  270. 270 CADGenBench submission anonymous_anon-edit-1787780317-d743_20260826-213840: anon-edit-1787780317-d743 version 0.1.0; unvalidated 28.6%
  271. 271 CADGenBench submission daanderson_fsmcp-opus-4-8_20260616-114515: FSMCP+Opus 4.8 version 0.1.0; unvalidated 28.5%
  272. 272 CADGenBench submission quartz17_quartz17_20260909-013330: quartz17 version 0.1.0; unvalidated 28.5%
  273. 273 CADGenBench submission arche_smith_20260702-225821: Smith version 0.1.0; unvalidated 28.3%
  274. 274 CADGenBench submission anonymous_anon-edi-1788896801-b000c8_20260908-194649: anon-edi-1788896801-b000c8 version 0.1.0; unvalidated 28.3%
  275. 275 Claude Sonnet 4.6 28.3%
  276. 276 CADGenBench submission joveh67_horu-8108_20261013-193641: horu-8108 version 0.1.0; unvalidated 28.3%
  277. 277 CADGenBench submission metax_qwen-38-local-agent-union-73-81_20261012-063726: qwen-38 local agent (union 73/81) version 0.1.0; unvalidated 28%
  278. 278 CADGenBench submission andrii-pytel_daedalus-phased-pipeline-opus-medium_20261004-083406: Daedalus - phased pipeline (opus, medium) version 0.1.0; unvalidated 27.9%
  279. 279 CADGenBench submission saysolid-adapted-hub-llc_saysolid-kimi-k3-exact-dataset-native-in_20260827-183525: SaySolid kimi-k3 exact-dataset-native-inputs worker 3d74eda951f1 version 0.1.0; unvalidated 27.9%
  280. 280 CADGenBench submission cal-b_cal-b_20260908-204810: cal-b version 0.1.0; unvalidated 27.7%
  281. 281 CADGenBench submission anonymous_anon-edi-1788841924-317e2e_20260908-043208: anon-edi-1788841924-317e2e version 0.1.0; unvalidated 27.6%
  282. 282 CADGenBench submission anonymous_g5b_20261026-140509: G5b version 0.1.0; unvalidated 27.6%
  283. 283 CADGenBench submission tohom76_lakare-6523_20261013-193625: lakare-6523 version 0.1.0; unvalidated 27.6%
  284. 284 CADGenBench submission cadsmith42_fable-5-1-agentic-editing_20260913-081127: fable-5-1-agentic-editing version 0.1.0; unvalidated 27.3%
  285. 285 CADGenBench submission hureho60_zuniri-4618_20261013-193655: zuniri-4618 version 0.1.0; unvalidated 27.2%
  286. 286 CADGenBench submission anonymous_run-d_20261030-132414: Run D version 0.1.0; unvalidated 27.2%
  287. 287 CADGenBench submission anonymous_run-j_20261106-092634: Run J version 0.1.0; unvalidated 27.1%
  288. 288 CADGenBench submission anonymous_o_20261108-175622: O version 0.1.0; unvalidated 26.9%
  289. 289 CADGenBench submission anonymous_test-submission_20260821-191118: test-submission version 0.1.0; unvalidated 26.9%
  290. 290 CADGenBench submission origogk_origogk-r5-contact-zero-rigid-edit_20260929-152629: OrigoGK r5 contact-zero rigid-edit version 0.1.0; unvalidated 26.8%
  291. 291 CADGenBench submission cal-a_cal-a_20260908-024134: cal-a version 0.1.0; unvalidated 26.7%
  292. 292 CADGenBench submission anonymous_run-l_20261107-122243: Run L version 0.1.0; unvalidated 26.7%
  293. 293 CADGenBench submission saysolid-adapted-hub-llc_saysolid-gpt-5-6-terra-exact-dataset-nat_20260826-024740: SaySolid gpt-5.6-terra exact-dataset-native-inputs worker 41bd4d911831 version 0.1.0; unvalidated 26.6%
  294. 294 CADGenBench submission reify_reify-deepseek-low-asi-all-edit-32-01_20261026-082500: reify-deepseek-low-asi-all-edit-32-01 version 0.1.0; unvalidated 26.4%
  295. 295 CADGenBench submission bruno-mutagent_mutagent-brepsmith-opus-5-xhigh-agentic-_20260828-132328: mutagent-brepsmith — Opus-5 xhigh agentic harness (editing-only) version 0.1.0; unvalidated 26.4%
  296. 296 CADGenBench submission cadybara-benchmark_exp005-run003-100-plus-copied-200_20260614-191528: EXP005 RUN003 100 plus copied 200 version 0.1.0; unvalidated 26.2%
  297. 297 CADGenBench submission cadybara_exp005-run003-100-plus-copied-200_20260614-192416: EXP005 RUN003 100 plus copied 200 version 0.1.0; unvalidated 26.1%
  298. 298 CADGenBench submission andrii-pytel_daedalus-one-shot-script-opus-medium_20261003-215858: Daedalus - one-shot script (opus, medium) version 0.1.0; unvalidated 26.1%
  299. 299 CADGenBench submission anonymous_run-g_20261105-082956: Run G version 0.1.0; unvalidated 26%
  300. 300 CADGenBench submission anonymous_cad-agent_20260821-172041: cad-agent version 0.1.0; unvalidated 25.9%
  301. 301 CADGenBench submission origogk_origogk-bounded-surface-diagnostic_20260927-182738: OrigoGK bounded surface diagnostic version 0.1.0; unvalidated 25.8%
  302. 302 CADGenBench submission origogk_origogk-planar-surface-diagnostic_20260927-160851: OrigoGK planar surface diagnostic version 0.1.0; unvalidated 25.8%
  303. 303 CADGenBench submission origogk_origogk-surface-quality-diagnostic_20260927-221023: OrigoGK surface quality diagnostic version 0.1.0; unvalidated 25.8%
  304. 304 CADGenBench submission w1ne_kernelcad-probe-genlane-v3-20261020_20261020-015604: kernelcad-probe-genlane-v3-20261020 version 0.1.0; unvalidated 25.7%
  305. 305 CADGenBench submission stealth_stealth-harness-haiku-5-5-xhigh_20261022-003154: Stealth Harness + Haiku 5.5 xHigh version 0.1.0; unvalidated 25.6%
  306. 306 CADGenBench submission anonymous_run-f_20261103-081936: Run F version 0.1.0; unvalidated 25.6%
  307. 307 CADGenBench submission anonymous_v_20261110-144608: V version 0.1.0; unvalidated 25.5%
  308. 308 CADGenBench submission anonymous_run-h_20261105-161202: Run H version 0.1.0; unvalidated 25.4%
  309. 309 CADGenBench submission anonymous_p_20261109-044130: P version 0.1.0; unvalidated 25.4%
  310. 310 CADGenBench submission anonymous_run-i_20261106-041307: Run I version 0.1.0; unvalidated 25.2%
  311. 311 CADGenBench submission anonymous_v0-5_20261106-002457: v0.5 version 0.1.0; unvalidated 25.2%
  312. 312 CADGenBench submission anonymous_q_20261109-090251: Q version 0.1.0; unvalidated 25.2%
  313. 313 CADGenBench submission origogk_origogk-retained-profile-surface-diagnos_20260927-050054: OrigoGK retained profile surface diagnostic version 0.1.0; unvalidated 25%
  314. 314 Gemini 3.1 Flash-Lite 24.9%
  315. 315 CADGenBench submission niziz67_homit-6594_20261007-061132: homit-6594 version 0.1.0; unvalidated 24.6%
  316. 316 CADGenBench submission rakshit-dwivedi_proxima_20260902-200639: Proxima version 0.1.0; unvalidated 24.6%
  317. 317 CADGenBench submission james-dillard_gpt-5-nano-candidate-l-pi-harness-five-s_20261001-001100: GPT-5 Nano Candidate L (Pi harness, five-stage workflow, 2026-09-30) version 0.1.0; unvalidated 24.5%
  318. 318 CADGenBench submission anonymous_r_20261109-113330: R version 0.1.0; unvalidated 24.3%
  319. 319 CADGenBench submission origogk_origogk-axial-step-edit-215-diagnostic_20260926-161403: OrigoGK axial STEP edit 215 diagnostic version 0.1.0; unvalidated 24%
  320. 320 CADGenBench submission anonymous_n_20261108-154638: N version 0.1.0; unvalidated 23.9%
  321. 321 CADGenBench submission miles-bimrose_qwen3-vl-235b-buil123d-ft-2stage_20260624-032814: Qwen3-VL-235B-buil123d-FT-2stage version 0.1.0; unvalidated 23.8%
  322. 322 CADGenBench submission anonymous_m_20261108-125233: M version 0.1.0; unvalidated 23.8%
  323. 323 CADGenBench submission anonymous_lq-1_20261108-121453: LQ_1 version 0.1.0; unvalidated 23.7%
  324. 324 CADGenBench submission local-user_t046-cgb-merge-101-150-mixed-v1_20261026-114525: t046-cgb-merge-101-150-mixed-v1 version 0.1.0; unvalidated 23.6%
  325. 325 CADGenBench submission miles-bimrose_qwen3-vl-235b-build123d-v6-lora-ckpt-150_20260618-225130: Qwen3-VL-235B build123d v6 (LoRA ckpt-15000) version 0.1.0; unvalidated 23.6%
  326. 326 CADGenBench submission jigem11_vomuko-4761_20261007-061022: vomuko-4761 version 0.1.0; unvalidated 23.6%
  327. 327 CADGenBench submission anonymous_t_20261110-100802: T version 0.1.0; unvalidated 23.5%
  328. 328 CADGenBench submission anonymous_s_20261109-134515: S version 0.1.0; unvalidated 23.4%
  329. 329 CADGenBench submission xueqinglin_glm-5-2-baseline-20260820-170417_20260820-091506: glm-5.2_baseline_20260820-170417 version 0.1.0; unvalidated 23.4%
  330. 330 CADGenBench submission anonymous_run-e_20261030-134619: Run E version 0.1.0; unvalidated 23.3%
  331. 331 CADGenBench submission anonymous_run-k_20261106-221903: Run K version 0.1.0; unvalidated 23.2%
  332. 332 CADGenBench submission origogk_origogk-sparse-suite-diagnostic_20260926-145739: OrigoGK sparse suite diagnostic version 0.1.0; unvalidated 22.9%
  333. 333 CADGenBench submission experiment_experiment_20260822-194005: Experiment version 0.1.0; unvalidated 22.8%
  334. 334 CADGenBench submission anonymous_run-c_20261030-144138: Run C version 0.1.0; unvalidated 22.7%
  335. 335 CADGenBench submission feorka44_indoin-5234_20261006-210352: indoin-5234 version 0.1.0; unvalidated 22.6%
  336. 336 CADGenBench submission anonymous_s46-a1_20261025-150639: S46-A1 version 0.1.0; unvalidated 22.5%
  337. 337 CADGenBench submission anonymous_run-b_20261030-140256: Run B version 0.1.0; unvalidated 22.5%
  338. 338 CADGenBench submission anonymous_s45-a1_20261021-131325: S45-A1 version 0.1.0; unvalidated 22.5%
  339. 339 CADGenBench submission arpado79_kaar-e88c_20261006-220543: kaar-e88c version 0.1.0; unvalidated 22.1%
  340. 340 CADGenBench submission ulwior35_givein-5069_20261006-213142: givein-5069 version 0.1.0; unvalidated 21.8%
  341. 341 CADGenBench submission miles-bimrose_qwen3-6-buil123d-ft-2stage_20260706-163128: Qwen3.6-buil123d-FT-2stage version 0.1.0; unvalidated 21.7%
  342. 342 CADGenBench submission james-dillard_gpt-5-nano-candidate-k-pi-harness-contro_20261001-022034: GPT-5 Nano Candidate K (Pi harness, control help, 2026-09-30) version 0.1.0; unvalidated 21.7%
  343. 343 CADGenBench submission miles-bimrose_drmstep-hybrid-v5_20260628-062259: drmstep-hybrid-v5 version 0.1.0; unvalidated 21.6%
  344. 344 CADGenBench submission anonymous_u_20261110-121946: U version 0.1.0; unvalidated 21.5%
  345. 345 CADGenBench submission arche_smith_20260709-234450: Smith version 0.1.0; unvalidated 21.4%
  346. 346 CADGenBench submission arche_smith_20260624-022436: Smith version 0.1.0; unvalidated 21.4%
  347. 347 CADGenBench submission siwoh56_hesutu-6163_20261007-061147: hesutu-6163 version 0.1.0; unvalidated 21.4%
  348. 348 CADGenBench submission anonymous_w_20261112-070217: W version 0.1.0; unvalidated 21.3%
  349. 349 CADGenBench submission anonymous_sa-v2_20261025-224542: SA-V2 version 0.1.0; unvalidated 21.2%
  350. 350 CADGenBench submission arche_smith_20260710-214646: Smith version 0.1.0; unvalidated 20.9%
  351. 351 CADGenBench submission saysolid-adapted-hub-llc_saysolid-gpt-6-astra-exact-dataset-nativ_20260914-205657: SaySolid gpt-6-astra exact-dataset-native-inputs editing-arm-only worker 46e6708c4207 version 0.1.0; unvalidated 20.9%
  352. 352 CADGenBench submission junde_junde-test_20260716-102222: junde-test version 0.1.0; unvalidated 20.8%
  353. 353 CADGenBench submission anonymous_v0-9_20261106-002525: v0.9 version 0.1.0; unvalidated 20.4%
  354. 354 CADGenBench submission anonymous_v0-2_20261105-153348: v0.2 version 0.1.0; unvalidated 20.4%
  355. 355 CADGenBench submission anonymous_v0-7_20261106-002511: v0.7 version 0.1.0; unvalidated 20.4%
  356. 356 CADGenBench submission anonymous_v0-4_20261105-153344: v0.4 version 0.1.0; unvalidated 20.1%
  357. 357 CADGenBench submission anonymous_v0-3_20261105-153341: v0.3 version 0.1.0; unvalidated 20.1%
  358. 358 CADGenBench submission bruno-mutagent_mutagent-brepsmith-sonnet-5-agentic-harn_20260827-080517: mutagent-brepsmith — Sonnet-5 agentic harness (editing-only) r3 version 0.1.0; unvalidated 20%
  359. 359 CADGenBench submission anon-170934_anon-170934_20260910-195151: anon_170934 version 0.1.0; unvalidated 19.9%
  360. 360 CADGenBench submission anonymous_anonymous-agent_20260917-082500: Anonymous agent version 0.1.0; unvalidated 19.8%
  361. 361 CADGenBench submission toparo-8937_gen17-toparo-8937_20261023-010520: gen17-toparo-8937 version 0.1.0; unvalidated 19.5%
  362. 362 CADGenBench submission anonymous_v0-1_20261105-153003: v0.1 version 0.1.0; unvalidated 19.5%
  363. 363 CADGenBench submission vasere-1792_gen17-vasere-1792_20261021-222031: gen17-vasere-1792 version 0.1.0; unvalidated 19.4%
  364. 364 CADGenBench submission indian-peafowl_india_20260718-185300: India version 0.1.0; unvalidated 19.2%
  365. 365 CADGenBench submission anonymous_anon-gen-1788819313-1f8489_20260907-221515: anon-gen-1788819313-1f8489 version 0.1.0; unvalidated 18.8%
  366. 366 CADGenBench submission anon-201155_sweep-e_20260910-210303: sweep-e version 0.1.0; unvalidated 18.5%
  367. 367 CADGenBench submission james-dillard_gpt-5-nano-candidate-c-pi-harness-2026-0_20260828-001340: GPT-5 Nano Candidate C (Pi harness, 2026-08-27) version 0.1.0; unvalidated 18.4%
  368. 368 CADGenBench submission temape-4542_gen16-temape-4542_20261023-010547: gen16-temape-4542 version 0.1.0; unvalidated 18.4%
  369. 369 GLM-4.6V 18.3%
  370. 370 CADGenBench submission gikabe-3612_gen16-gikabe-3612_20261021-221910: gen16-gikabe-3612 version 0.1.0; unvalidated 18.3%
  371. 371 CADGenBench submission cad-mcp-research_generation49-matched-evaluation-cell-248_20260824-080450: generation49 matched evaluation cell-2485f2e31202edef62dc version 0.1.0; unvalidated 18.3%
  372. 372 CADGenBench submission cad-mcp-research_baseline-protected-v0-7-11-all-generatio_20260824-183530: baseline-protected v0.7.11 all-generation CAD-MCP v0.7 version 0.1.0; unvalidated 18.1%
  373. 373 CADGenBench submission origogk_origogk-sparse-suite-snapshot_20260926-142938: OrigoGK sparse suite snapshot version 0.1.0; unvalidated 18%
  374. 374 CADGenBench submission anonymous_run-5f161034-1787724840_20260826-061750: run-5f161034-1787724840 version 0.1.0; unvalidated 18%
  375. 375 CADGenBench submission cad-mcp-research_baseline-protected-v0-7-11-all-generatio_20260824-182537: baseline-protected v0.7.11 all-generation Vanilla checkpoints version 0.1.0; unvalidated 18%
  376. 376 CADGenBench submission james-dillard_gpt-5-nano-candidate-j-pi-harness-2026-0_20260919-083944: GPT-5 Nano Candidate J (Pi harness, 2026-09-17) version 0.1.0; unvalidated 17.6%
  377. 377 CADGenBench submission giluze-5666_gen16-giluze-5666_20261022-184734: gen16-giluze-5666 version 0.1.0; unvalidated 17.6%
  378. 378 CADGenBench submission cad-mcp-research_generation49-matched-evaluation-cell-8ee_20260824-081358: generation49 matched evaluation cell-8ee597dcef821bf18cf7 version 0.1.0; unvalidated 17.4%
  379. 379 CADGenBench submission james-dillard_gpt-5-nano-candidate-e-pi-harness-2026-0_20260828-044843: GPT-5 Nano Candidate E (Pi harness, 2026-08-27) version 0.1.0; unvalidated 17.3%
  380. 380 CADGenBench submission anonymous_test-submission_20260819-015853: test-submission version 0.1.0; unvalidated 17.2%
  381. 381 CADGenBench submission origogk_origogk-contact-fix-adaptive-step_20260929-101124: OrigoGK contact-fix adaptive-step version 0.1.0; unvalidated 17.1%
  382. 382 CADGenBench submission arche_smith_20260709-222512: Smith version 0.1.0; unvalidated 17.1%
  383. 383 CADGenBench submission debumo-6710_gen16-debumo-6710_20261020-214856: gen16-debumo-6710 version 0.1.0; unvalidated 17%
  384. 384 CADGenBench submission sibule-7638_gen16-sibule-7638_20261023-010458: gen16-sibule-7638 version 0.1.0; unvalidated 16.9%
  385. 385 CADGenBench submission origogk_origogk-full-81-task-run-20260926_20260926-223823: OrigoGK full 81-task run 20260926 version 0.1.0; unvalidated 16.8%
  386. 386 CADGenBench submission gen-harness-b_gen-harness-b_20260910-195259: gen-harness-b version 0.1.0; unvalidated 16.8%
  387. 387 CADGenBench submission sesado-1438_gen16-sesado-1438_20261021-153018: gen16-sesado-1438 version 0.1.0; unvalidated 16.8%
  388. 388 Qwen3-VL-235B-A22B-Instruct 16.8%
  389. 389 CADGenBench submission yeshenpy_qwen-ablation_20260903-115457: Qwen ablation version 0.1.0; unvalidated 16.7%
  390. 390 CADGenBench submission anonymous_o-a1_20261021-140503: O-A1 version 0.1.0; unvalidated 16.6%
  391. 391 CADGenBench submission cad-mcp-blinded-study_cell-060ff6bdc2e19155fec8_20260821-084921: cell-060ff6bdc2e19155fec8 version 0.1.0; unvalidated 16.3%
  392. 392 CADGenBench submission arche_smith_20260624-011205: Smith version 0.1.0; unvalidated 16.3%
  393. 393 CADGenBench submission baseline-v7_baseline-v7_20260910-195324: baseline-v7 version 0.1.0; unvalidated 16.3%
  394. 394 CADGenBench submission cad-mcp-blinded-study_cell-04d75a55d41904fd073d_20260816-214010: cell-04d75a55d41904fd073d version 0.1.0; unvalidated 16.2%
  395. 395 CADGenBench submission yerin-choi_cad-mcp-paired-heldout-v1-vanilla-replic_20260814-143514: CAD-MCP paired heldout v1 vanilla replicate 3 version 0.1.0; unvalidated 16.1%
  396. 396 CADGenBench submission cad-mcp-blinded-study_cell-08f852f7019f1b414b3a_20260821-085827: cell-08f852f7019f1b414b3a version 0.1.0; unvalidated 16.1%
  397. 397 CADGenBench submission experiment_experiment-partial-32-81-diagnostic_20260821-231550: Experiment - partial 32/81 diagnostic version 0.1.0; unvalidated 16%
  398. 398 CADGenBench submission james-dillard_gpt-5-nano-candidate-h-pi-harness-2026-0_20260901-101026: GPT-5 Nano Candidate H (Pi harness, 2026-08-31) version 0.1.0; unvalidated 15.8%
  399. 399 CADGenBench submission cad-mcp-blinded-study_cell-1f61f132aa5bd4b4be8c_20260821-090655: cell-1f61f132aa5bd4b4be8c version 0.1.0; unvalidated 15.8%
  400. 400 CADGenBench submission rigazu-5835_edit16-rigazu-5835_20261030-011458: edit16-rigazu-5835 version 0.1.0; unvalidated 15.6%
  401. 401 CADGenBench submission yerin-choi_cad-mcp-paired-heldout-v1-cad-mcp-replic_20260814-143420: CAD-MCP paired heldout v1 cad_mcp replicate 2 version 0.1.0; unvalidated 15.6%
  402. 402 CADGenBench submission local-user_codex-current-original-49-20261018-01_20261018-114008: codex-current-original-49-20261018-01 version 0.1.0; unvalidated 15.4%
  403. 403 CADGenBench submission cad-mcp-blinded-study_cell-83efce1eb738ad54f712_20260821-091255: cell-83efce1eb738ad54f712 version 0.1.0; unvalidated 15.4%
  404. 404 CADGenBench submission arche_smith_20260709-215857: Smith version 0.1.0; unvalidated 15.4%
  405. 405 CADGenBench submission cad-mcp-blinded-study_cell-92f624fa3400d7055063_20260816-220722: cell-92f624fa3400d7055063 version 0.1.0; unvalidated 15.3%
  406. 406 CADGenBench submission yerin-choi_cad-mcp-paired-heldout-v1-vanilla-replic_20260814-143318: CAD-MCP paired heldout v1 vanilla replicate 2 version 0.1.0; unvalidated 15.3%
  407. 407 CADGenBench submission ronado-1508_edit16-ronado-1508_20261024-154510: edit16-ronado-1508 version 0.1.0; unvalidated 15.3%
  408. 408 CADGenBench submission goliki-7696_edit16-goliki-7696_20261024-154539: edit16-goliki-7696 version 0.1.0; unvalidated 15.2%
  409. 409 CADGenBench submission cad-mcp-blinded-study_cell-f8302b92ab6b809510a9_20260821-092551: cell-f8302b92ab6b809510a9 version 0.1.0; unvalidated 15.1%
  410. 410 CADGenBench submission huggingface_gpt-5-6-sol-hf-baseline-pipeline-test_20260807-094609: GPT-5.6 Sol HF Baseline (pipeline test) version 0.1.0; unvalidated 15%
  411. 411 CADGenBench submission fefona-2711_edit16-fefona-2711_20261030-011434: edit16-fefona-2711 version 0.1.0; unvalidated 14.9%
  412. 412 CADGenBench submission cad-mcp-blinded-study_cell-c9bba894d207e6be92fd_20260816-221300: cell-c9bba894d207e6be92fd version 0.1.0; unvalidated 14.9%
  413. 413 CADGenBench submission arche_smith_20260709-215034: Smith version 0.1.0; unvalidated 14.8%
  414. 414 CADGenBench submission yerin-choi_cad-mcp-paired-heldout-v1-cad-mcp-replic_20260814-143202: CAD-MCP paired heldout v1 cad_mcp replicate 1 version 0.1.0; unvalidated 14.8%
  415. 415 CADGenBench submission cad-mcp-blinded-study_cell-4603538f259e6df50d72_20260816-215447: cell-4603538f259e6df50d72 version 0.1.0; unvalidated 14.7%
  416. 416 CADGenBench submission yerin-choi_cad-mcp-paired-heldout-v1-vanilla-replic_20260814-142911: CAD-MCP paired heldout v1 vanilla replicate 1 version 0.1.0; unvalidated 14.6%
  417. 417 CADGenBench submission daanderson_fsmcp-opus-4-8-stl_20260616-122528: FSMCP+Opus 4.8 - STL version 0.1.0; unvalidated 14.6%
  418. 418 CADGenBench submission arche_smith_20260709-212542: Smith version 0.1.0; unvalidated 14.4%
  419. 419 CADGenBench submission cad-mcp-blinded-study_cell-85da63afedcb6c20f060_20260816-220149: cell-85da63afedcb6c20f060 version 0.1.0; unvalidated 14.3%
  420. 420 CADGenBench submission yerin-choi_cad-mcp-paired-heldout-v1-cad-mcp-replic_20260814-143620: CAD-MCP paired heldout v1 cad_mcp replicate 3 version 0.1.0; unvalidated 14.2%
  421. 421 CADGenBench submission anonymous_run-3283c228-1787609057_20260824-222220: run-3283c228-1787609057 version 0.1.0; unvalidated 14%
  422. 422 CADGenBench submission anonymous_run-3283c228-1787609057_20260824-232333: run-3283c228-1787609057 version 0.1.0; unvalidated 14%
  423. 423 CADGenBench submission cad-mcp-blinded-study_cell-329c6ab62a4397e86819_20260816-214811: cell-329c6ab62a4397e86819 version 0.1.0; unvalidated 13.9%
  424. 424 CADGenBench submission cad-mcp-blinded-study_cell-d5fe8f58a164aa9aee2a_20260821-092007: cell-d5fe8f58a164aa9aee2a version 0.1.0; unvalidated 13.7%
  425. 425 CADGenBench submission anonymous_anon-edi-1788819332-ce4901_20260907-221535: anon-edi-1788819332-ce4901 version 0.1.0; unvalidated 13.5%
  426. 426 CADGenBench submission yeshenpy_a-r2_20260902-081542: A-r2 version 0.1.0; unvalidated 13.5%
  427. 427 CADGenBench submission anonymous_run-4934da30-1787675208_20260825-163254: run-4934da30-1787675208 version 0.1.0; unvalidated 13.4%
  428. 428 CADGenBench submission anonymous_run-5f161034-1787686551_20260825-193825: run-5f161034-1787686551 version 0.1.0; unvalidated 13.4%
  429. 429 CADGenBench submission anonymous_run-797978e8-1787636081_20260825-053639: run-797978e8-1787636081 version 0.1.0; unvalidated 12.5%
  430. 430 CADGenBench submission anonymous_run-ca7da17d-1787680716_20260825-180307: run-ca7da17d-1787680716 version 0.1.0; unvalidated 12.4%
  431. 431 CADGenBench submission anonymous_run-863e3c01-1788312265_20260902-012426: run-863e3c01-1788312265 version 0.1.0; unvalidated 12.4%
  432. 432 CADGenBench submission james-dillard_gpt-5-nano-candidate-a-pi-harness-2026-0_20260827-100706: GPT-5 Nano Candidate A (Pi harness, 2026-08-26) version 0.1.0; unvalidated 12.4%
  433. 433 CADGenBench submission phi-linh_cad-gen-gpt-5-mini-v1_20260713-215232: cad-gen gpt-5-mini v1 version 0.1.0; unvalidated 12.3%
  434. 434 CADGenBench submission phi-linh_cad-gen-gpt-5-mini-v1_20260713-215219: cad-gen gpt-5-mini v1 version 0.1.0; unvalidated 12.3%
  435. 435 CADGenBench submission anonymous_anonymous-agent_20260916-133147: Anonymous agent version 0.1.0; unvalidated 12.3%
  436. 436 CADGenBench submission anonymous_run-46e66701-1787624064_20260825-040828: run-46e66701-1787624064 version 0.1.0; unvalidated 12.2%
  437. 437 CADGenBench submission anonymous_run-8baebabe-1788313256_20260902-014057: run-8baebabe-1788313256 version 0.1.0; unvalidated 12%
  438. 438 CADGenBench submission arche_smith_20260708-000637: Smith version 0.1.0; unvalidated 11.6%
  439. 439 CADGenBench submission arche_smith_20260708-062950: Smith version 0.1.0; unvalidated 11.5%
  440. 440 CADGenBench submission anonymous_anonymous-agent_20260916-183114: Anonymous agent version 0.1.0; unvalidated 11.4%
  441. 441 CADGenBench submission arche_smith_20260708-065352: Smith version 0.1.0; unvalidated 11.4%
  442. 442 CADGenBench submission arche_smith_20260623-230519: Smith version 0.1.0; unvalidated 11.4%
  443. 443 CADGenBench submission arche_smith_20260624-001648: Smith version 0.1.0; unvalidated 11.4%
  444. 444 CADGenBench submission james-dillard_gpt-5-nano-candidate-d-pi-harness-2026-0_20260828-025518: GPT-5 Nano Candidate D (Pi harness, 2026-08-27) version 0.1.0; unvalidated 10.9%
  445. 445 CADGenBench submission yitong42_codex-gpt-5-6-sol-high-15-sample_20260811-162034: Codex + gpt-5.6-sol high (15-sample) version 0.1.0; unvalidated 10.5%
  446. 446 CADGenBench submission origogk_origogk-1mm-full-input-diagnostic_20260929-052612: OrigoGK 1mm full-input diagnostic version 0.1.0; unvalidated 10.5%
  447. 447 CADGenBench submission cadse_brief-v7-fable-5-2-builder-effort-high-9_20261112-185357: brief v7, Fable 5.2 builder effort high, 9 fixtures (seed 20261112) version 0.1.0; unvalidated 10.1%
  448. 448 CADGenBench submission anonymous_anon-gen-1788761670-72e736_20260907-061431: anon-gen-1788761670-72e736 version 0.1.0; unvalidated 9.92%
  449. 449 CADGenBench submission pave-cad_pave-cad-tool-assisted-no-skill-build123_20260712-165946: PAVE-CAD tool_assisted_no_skill_build123d.v2 (cadgenbench_langgraph_qwen37_plus_20260526) version 0.1.0; unvalidated 9.86%
  450. 450 CADGenBench submission daanderson_fs-mcp-opus-4-8-minimal-harness_20260615-131636: FS MCP - Opus 4.8 - Minimal Harness version 0.1.0; unvalidated 9.83%
  451. 451 CADGenBench submission cadse_review-arm-brief-v7-builds-after-blind-r_20261112-155250: Review arm: brief v7 builds after blind review and fix, nine fixtures version 0.1.0; unvalidated 9.72%
  452. 452 CADGenBench submission cadse_small-offset-r7x-effort-xhigh-solids-shi_20261112-111053: small offset r7x: effort xhigh solids shifted by 0.7 % of the diagonal (alignment test), 9 random fixtures (seed 20261112) version 0.1.0; unvalidated 9.68%
  453. 453 CADGenBench submission cadse_brief-v7-on-dyno-nine-fixtures-effort-ma_20261112-151818: Brief v7 on dyno: nine fixtures, effort max, one build per part version 0.1.0; unvalidated 9.63%
  454. 454 CADGenBench submission timeci-8199_gen8-timeci-8199_20261018-155944: gen8-timeci-8199 version 0.1.0; unvalidated 9.50%
  455. 455 CADGenBench submission miles-bimrose_qwen3-vl-8b-build123d-finetune_20260611-212111: Qwen3-VL-8B build123d finetune version 0.1.0; unvalidated 9.42%
  456. 456 CADGenBench submission yitong42_pi-agent-gpt-5-6-sol-high-15-sample_20260811-164701: Pi Agent + gpt-5.6-sol high (15-sample) version 0.1.0; unvalidated 9.27%
  457. 457 CADGenBench submission cadse_effort-xhigh-r7x-full-brief-principles-h_20261112-095633: effort xhigh r7x: full brief + principles + hole rules v2, Opus builder, 9 random fixtures (seed 20261112) version 0.1.0; unvalidated 9.26%
  458. 458 CADGenBench submission cadse_guarded-offset-r5-round-5-solids-shifted_20261112-093438: guarded offset r5: round 5 solids shifted 1.5 % unless near-symmetric (alignment test), 9 random fixtures (seed 20261112) version 0.1.0; unvalidated 8.97%
  459. 459 CADGenBench submission cadse_small-offset-r5-round-5-solids-shifted-b_20261112-111149: small offset r5: round 5 solids shifted by 0.7 % of the diagonal (alignment test), 9 random fixtures (seed 20261112) version 0.1.0; unvalidated 8.97%
  460. 460 CADGenBench submission cadse_pose-rotx-r5-round-5-solids-turned-180-d_20261112-090958: pose rotx r5: round 5 solids turned 180 deg about x (alignment test), 9 random fixtures (seed 20261112) version 0.1.0; unvalidated 8.90%
  461. 461 CADGenBench submission pzfreo_build123d-mcp-0-3-85-dev0-gpt-6-astra-hi_20260905-060736: build123d-mcp-0.3.85.dev0-gpt-6-astra-high version 0.1.0; unvalidated 8.84%
  462. 462 CADGenBench submission james-dillard_gpt-5-nano-candidate-b-pi-harness-2026-0_20260827-101758: GPT-5 Nano Candidate B (Pi harness, 2026-08-26) version 0.1.0; unvalidated 8.79%
  463. 463 CADGenBench submission alexchunlin_claude-opus-5-5-blender-cadlib-drawing-t_20261027-223010: Claude Opus 5.5 + Blender/cadlib + drawing tools (OCR, measure, holes, overlay), faceted STEP (10-sample) version 0.1.0; unvalidated 8.78%
  464. 464 CADGenBench submission cadse_small-offset-lean3-hole-rules-v2-lean-so_20261112-111231: small offset lean3: hole rules v2 lean solids shifted by 0.7 % of the diagonal (alignment test), 9 random fixtures (seed 20261112) version 0.1.0; unvalidated 8.76%
  465. 465 CADGenBench submission cadse_small-offset-r6-round-6-solids-shifted-b_20261112-092806: small offset r6: round 6 solids shifted by 0.7 % of the diagonal (alignment test), 9 random fixtures (seed 20261112) version 0.1.0; unvalidated 8.69%
  466. 466 CADGenBench submission cadse_economy-mode-off-buildbox-principles-v4-_20261112-071308: economy mode off: buildbox principles v4 + scoring-aware brief + zoom, Opus builder, 9 random fixtures (seed 20261112) version 0.1.0; unvalidated 8.68%
  467. 467 CADGenBench submission cadse_offset-lean3-hole-rules-v2-lean-solids-s_20261112-090323: offset lean3: hole rules v2 lean solids shifted by 1.5 % of the diagonal (alignment test), 9 random fixtures (seed 20261112) version 0.1.0; unvalidated 8.66%
  468. 468 CADGenBench submission origogk_origogk-generation-housing-diagnostic-20_20260926-060753: OrigoGK generation housing diagnostic 20260926 version 0.1.0; unvalidated 8.63%
  469. 469 CADGenBench submission alexchunlin_claude-opus-5-5-plain-build123d-10-sampl_20261027-144651: Claude Opus 5.5 + plain build123d (10-sample pilot, comparison arm) version 0.1.0; unvalidated 8.63%
  470. 470 CADGenBench submission cadse_pose-rotz-r5-round-5-solids-turned-180-d_20261112-090903: pose rotz r5: round 5 solids turned 180 deg about z (alignment test), 9 random fixtures (seed 20261112) version 0.1.0; unvalidated 8.63%
  471. 471 CADGenBench submission borisyich_freecad-mcp-v1-37-gpt-5-6-high-some_20260817-090235: freecad-mcp-v1.37-gpt-5.6-high-some version 0.1.0; unvalidated 8.60%
  472. 472 CADGenBench submission cadse_offset-r6-round-6-solids-shifted-by-1-5-_20261112-090242: offset r6: round 6 solids shifted by 1.5 % of the diagonal (alignment test), 9 random fixtures (seed 20261112) version 0.1.0; unvalidated 8.60%
  473. 473 CADGenBench submission cadse_pose-roty-r5-round-5-solids-turned-180-d_20261112-091042: pose roty r5: round 5 solids turned 180 deg about y (alignment test), 9 random fixtures (seed 20261112) version 0.1.0; unvalidated 8.60%
  474. 474 CADGenBench submission cadse_round-6-full-brief-principles-hole-rules_20261112-083429: round 6: full brief + principles + hole rules v2, Opus builder, 9 random fixtures (seed 20261112) version 0.1.0; unvalidated 8.36%
  475. 475 CADGenBench submission pzfreo_opus5-xhigh-official-baseline-prompt-nom_20260809-222310: opus5-xhigh-official-baseline-prompt-nomcp-partial11-r1 version 0.1.0; unvalidated 8.34%
  476. 476 CADGenBench submission cadse_hole-rules-v2-lean-prompt-zoom-opus-buil_20261112-080413: hole rules v2: lean prompt + zoom, Opus builder, 9 random fixtures (seed 20261112) version 0.1.0; unvalidated 8.31%
  477. 477 CADGenBench submission cadse_passage-and-hole-rules-lean-prompt-zoom-_20261112-072345: passage and hole rules: lean prompt + zoom, Opus builder, 9 random fixtures (seed 20261112) version 0.1.0; unvalidated 8.18%
  478. 478 CADGenBench submission cadse_repeat-r5b-full-brief-principles-v4-unch_20261112-102013: repeat r5b: full brief + principles v4, unchanged repeat of round 5, Opus builder, 9 random fixtures (seed 20261112) version 0.1.0; unvalidated 7.97%
  479. 479 CADGenBench submission alexchunlin_claude-opus-5-5-headless-blender-cadlib-_20261027-150637: Claude Opus 5.5 + headless Blender/cadlib, faceted STEP (10-sample pilot) version 0.1.0; unvalidated 7.94%
  480. 480 CADGenBench submission alexchunlin_claude-opus-5-5-blender-cadlib-faceted-s_20261027-215115: Claude Opus 5.5 + Blender/cadlib, faceted STEP (10-sample repeat, no drawing tools) version 0.1.0; unvalidated 7.87%
  481. 481 CADGenBench submission cadse_repeat-2-lean-prompt-no-principles-zoom-_20261112-071803: repeat 2: lean prompt (no principles) + zoom, Opus builder, 9 random fixtures (seed 20261112) version 0.1.0; unvalidated 7.61%
  482. 482 CADGenBench submission petrichor_petrichor_20260909-071845: petrichor version 0.1.0; unvalidated 7.56%
  483. 483 CADGenBench submission cadse_lean-prompt-no-principles-zoom-opus-buil_20261112-055409: lean prompt (no principles) + zoom, Opus builder, 9 random fixtures (seed 20261112) version 0.1.0; unvalidated 7.51%
  484. 484 CADGenBench submission min-liu_chamfer-t1-edit-smoke15_20260709-013607: chamfer-t1-edit-smoke15 version 0.1.0; unvalidated 7.30%
  485. 485 CADGenBench submission origogk_origogk-analytic-edits-diagnostic-202609_20260926-044655: OrigoGK analytic edits diagnostic 20260926 version 0.1.0; unvalidated 7.06%
  486. 486 CADGenBench submission cadse_sheet-notes-r1-full-brief-principles-bui_20261112-111817: sheet notes r1: full brief + principles + build123d sheet-metal notes, 7 sheet-metal parts only, Opus builder (seed 20261112) version 0.1.0; unvalidated 6.79%
  487. 487 CADGenBench submission pzfreo_gpt-5-5-b123d-mcp-0-3-59-xhigh-smoke10-p_20260701-131749: gpt-5.5-b123d-mcp-0.3.59-xhigh-SMOKE10-P1 version 0.1.0; unvalidated 6.73%
  488. 488 CADGenBench submission anon-181240_sweep-c2_20260910-202002: sweep-c2 version 0.1.0; unvalidated 6.66%
  489. 489 CADGenBench submission cadse_buildbox-principles-v3-compare-loop-opus_20261112-040654: buildbox principles v3 + compare loop, Opus builder, 9 random fixtures (seed 20261112) version 0.1.0; unvalidated 6.63%
  490. 490 CADGenBench submission pzfreo_build123d-mcp-0-3-90-gemini-4-argon-high_20261021-205929: build123d-mcp-0.3.90-gemini-4-argon-high version 0.1.0; unvalidated 6.51%
  491. 491 CADGenBench submission cadse_buildbox-principles-v4-scoring-aware-bri_20261112-051241: buildbox principles v4 + scoring-aware brief + zoom, Opus builder, 9 random fixtures (seed 20261112) version 0.1.0; unvalidated 6.43%
  492. 492 CADGenBench submission reify_reify-sol-low-asi-202-209-paired-01_20261021-220527: reify-sol-low-asi-202-209-paired-01 version 0.1.0; unvalidated 6.35%
  493. 493 CADGenBench submission cadse_hand-edited-diagnostic-probes-on-3-fixtu_20261112-061555: hand-edited diagnostic probes on 3 fixtures (single change each), other 6 = earlier run r3 version 0.1.0; unvalidated 6.34%
  494. 494 CADGenBench submission cadse_buildbox-principles-v4-drawing-rules-com_20261112-043202: buildbox principles v4 (drawing rules) + compare loop, Opus builder, 9 random fixtures (seed 20261112) version 0.1.0; unvalidated 6.25%
  495. 495 CADGenBench submission cadse_buildbox-principles-opus-builder-9-rando_20261112-033752: buildbox principles + Opus builder, 9 random fixtures (seed 20261112) version 0.1.0; unvalidated 6.14%
  496. 496 CADGenBench submission pzfreo_build123d-mcp-0-3-83-fable-5-1-high_20260902-121723: build123d-mcp-0.3.83-fable-5.1-high version 0.1.0; unvalidated 6.09%
  497. 497 CADGenBench submission yitong42_matched-baseline-codex-gpt-5-6-sol-high-_20260906-170553: Matched baseline + Codex gpt-5.6-sol high (10-case) version 0.1.0; unvalidated 6.08%
  498. 498 CADGenBench submission lolopu-8948_edit8-lolopu-8948_20261030-011549: edit8-lolopu-8948 version 0.1.0; unvalidated 6.04%
  499. 499 CADGenBench submission local-user_t047-inspect-feedback-six-20261029_20261029-155032: t047-inspect-feedback-six-20261029 version 0.1.0; unvalidated 5.95%
  500. 500 CADGenBench submission origogk_origogk-sparse-dual-full-input-diagnosti_20260928-160948: OrigoGK sparse-dual full-input diagnostic version 0.1.0; unvalidated 5.91%
  501. 501 CADGenBench submission reify_reify-sol-low-naked-202-209-paired-01_20261021-220143: reify-sol-low-naked-202-209-paired-01 version 0.1.0; unvalidated 5.90%
  502. 502 CADGenBench submission pzfreo_pzfreo_20260902-062348: pzfreo version 0.1.0; unvalidated 5.83%
  503. 503 CADGenBench submission yitong42_m2d-first-codex-gpt-5-6-sol-high-10-case_20260906-170530: M2D-first + Codex gpt-5.6-sol high (10-case) version 0.1.0; unvalidated 5.82%
  504. 504 CADGenBench submission local-user_t047-autonomous-feedback-six-20261030_20261030-010719: t047-autonomous-feedback-six-20261030 version 0.1.0; unvalidated 5.82%
  505. 505 CADGenBench submission pzfreo_gpt55-v0368-smoke10_20260705-172407: gpt55-v0368-smoke10 version 0.1.0; unvalidated 5.81%
  506. 506 CADGenBench submission pzfreo_gpt-5-5-b123d-mcp-0-3-59-xhigh-smoke10-n_20260627-171359: gpt-5.5-b123d-mcp-0.3.59-xhigh-SMOKE10-newprompt version 0.1.0; unvalidated 5.75%
  507. 507 CADGenBench submission reify_reify-deepseek-low-asi-217-238-01_20261023-070657: reify-deepseek-low-asi-217-238-01 version 0.1.0; unvalidated 5.70%
  508. 508 CADGenBench submission cad-study_baseline-no-planning_20261007-140142: baseline-no_planning version 0.1.0; unvalidated 5.65%
  509. 509 CADGenBench submission anonymous_anon-gen-1788670318-98a7_20260906-045201: anon-gen-1788670318-98a7 version 0.1.0; unvalidated 5.64%
  510. 510 CADGenBench submission anonymous_anon-gen-1788746242-74b911_20260907-015723: anon-gen-1788746242-74b911 version 0.1.0; unvalidated 5.61%
  511. 511 CADGenBench submission anonymous_anon-gen-1788680583-e9d0_20260906-074305: anon-gen-1788680583-e9d0 version 0.1.0; unvalidated 5.48%
  512. 512 CADGenBench submission anonymous_anon-gen-1788717334-a056_20260906-175535: anon-gen-1788717334-a056 version 0.1.0; unvalidated 5.45%
  513. 513 CADGenBench submission pzfreo_agy-gemini37-flash-high-plan-mcp0383-smo_20260901-190641: agy-gemini37-flash-high-plan-mcp0383-smoke6 version 0.1.0; unvalidated 5.28%
  514. 514 CADGenBench submission pzfreo_gpt55-pr40-pr403-smoke10_20260708-215753: gpt55-pr40-pr403-smoke10 version 0.1.0; unvalidated 5.24%
  515. 515 CADGenBench submission local-user_t047-tool021-tx-a-20261029_20261029-060246: t047-tool021-tx-a-20261029 version 0.1.0; unvalidated 5.19%
  516. 516 CADGenBench submission cad-study_baseline-graph-cad-planning_20261007-230611: baseline-graph_cad_planning version 0.1.0; unvalidated 5.03%
  517. 517 CADGenBench submission tamarind_tamarind_20260909-152727: tamarind version 0.1.0; unvalidated 4.95%
  518. 518 CADGenBench submission anonymous_anon-edi-1788761677-0e4b7e_20260907-061438: anon-edi-1788761677-0e4b7e version 0.1.0; unvalidated 4.89%
  519. 519 CADGenBench submission origogk_origogk-bounded-dual-full-input-diagnost_20260928-141343: OrigoGK bounded-dual full-input diagnostic version 0.1.0; unvalidated 4.87%
  520. 520 CADGenBench submission cad-study_baseline-cadcoder-planning_20261007-193721: baseline-cadcoder_planning version 0.1.0; unvalidated 4.81%
  521. 521 CADGenBench submission pzfreo_pzfreo-gpt55-v0375-smoke10-mcp_20260709-104821: pzfreo_gpt55-v0375-smoke10-mcp version 0.1.0; unvalidated 4.68%
  522. 522 CADGenBench submission cad-study_baseline-general-coding-plan_20261007-174344: baseline-general_coding-plan version 0.1.0; unvalidated 4.66%
  523. 523 CADGenBench submission local-user_t047-r3-b-r01-20261027_20261027-081850: t047-r3-b-r01-20261027 version 0.1.0; unvalidated 4.62%
  524. 524 CADGenBench submission cad-study_baseline-no-plan-rerun_20261008-045844: baseline_no_plan_rerun version 0.1.0; unvalidated 4.61%
  525. 525 CADGenBench submission reify_reify-deepseek-low-naked-217-238-paralle_20261023-030248: reify-deepseek-low-naked-217-238-parallel-01 version 0.1.0; unvalidated 4.59%
  526. 526 CADGenBench submission pzfreo_fable5-v0360-med-eff-smoke5_20260702-042807: fable5-v0360-med-eff-smoke5 version 0.1.0; unvalidated 4.57%
  527. 527 CADGenBench submission anonymous_anon-gen-1787740768-01a0_20260826-103929: anon-gen-1787740768-01a0 version 0.1.0; unvalidated 4.55%
  528. 528 CADGenBench submission yitong42_native-gpt-6-astra-ultra-baseline-4-case_20260917-050440: Native GPT-6 Astra Ultra baseline 4-case 20260916-235800 version 0.1.0; unvalidated 4.55%
  529. 529 CADGenBench submission anonymous_anon-gen-1788675770-a7c0_20260906-062252: anon-gen-1788675770-a7c0 version 0.1.0; unvalidated 4.48%
  530. 530 CADGenBench submission pzfreo_build123d-mcp-0-3-84-dev0-gemini-3-8-fla_20260903-113023: build123d-mcp-0.3.84.dev0-gemini-3.8-flash-high-recognition-editing6-r2 version 0.1.0; unvalidated 4.46%
  531. 531 CADGenBench submission yitong42_native-gpt-6-astra-ultra-svg-first-4-cas_20260917-050647: Native GPT-6 Astra Ultra svg-first 4-case 20260916-235800 version 0.1.0; unvalidated 4.41%
  532. 532 CADGenBench submission reify_reify-sol-low-asi-217-238-parallel-01_20261023-030814: reify-sol-low-asi-217-238-parallel-01 version 0.1.0; unvalidated 4.37%
  533. 533 CADGenBench submission cajuce-1755_gen4-cajuce-1755_20261017-164050: gen4-cajuce-1755 version 0.1.0; unvalidated 4.35%
  534. 534 CADGenBench submission miles-bimrose_qwen3-vl-2b-build123d-finetune_20260609-204140: Qwen3-VL-2B build123d finetune version 0.1.0; unvalidated 4.34%
  535. 535 CADGenBench submission cad-study_baseline-no-planning-corrected_20261010-041632: baseline-no_planning_corrected version 0.1.0; unvalidated 4.30%
  536. 536 CADGenBench submission anonymous_anon-gen-1787964784-d19c_20260829-005305: anon-gen-1787964784-d19c version 0.1.0; unvalidated 4.29%
  537. 537 CADGenBench submission anonymous_anon-gen-1787967441-5839_20260829-013722: anon-gen-1787967441-5839 version 0.1.0; unvalidated 4.29%
  538. 538 CADGenBench submission pzfreo_gpt-5-5-b123d-mcp-0-3-59-xhigh-resmoke7-_20260627-192314: gpt-5.5-b123d-mcp-0.3.59-xhigh-RESMOKE7-fixed version 0.1.0; unvalidated 4.27%
  539. 539 CADGenBench submission reify_reify-sol-low-asi-211-215-config-01_20261022-062053: reify-sol-low-asi-211-215-config-01 version 0.1.0; unvalidated 4.26%
  540. 540 CADGenBench submission local-user_t047-full-mid-feedback-six-20261030_20261029-192823: t047-full-mid-feedback-six-20261030 version 0.1.0; unvalidated 4.13%
  541. 541 CADGenBench submission pidebe-5079_gen4-pidebe-5079-r2_20261016-172912: gen4-pidebe-5079-r2 version 0.1.0; unvalidated 4.03%
  542. 542 CADGenBench submission anonymous_anon-gen-1788548779-3c7e_20260904-190620: anon-gen-1788548779-3c7e version 0.1.0; unvalidated 3.94%
  543. 543 CADGenBench submission local-user_t047-0770-b-dev4-20261027_20261026-190236: t047-0770-B-dev4-20261027 version 0.1.0; unvalidated 3.87%
  544. 544 CADGenBench submission anonymous_anon-gen-1789088535-1624c8_20260911-010919: anon-gen-1789088535-1624c8 version 0.1.0; unvalidated 3.84%
  545. 545 CADGenBench submission local-user_t047-0771-p-dev4-20261027_20261026-190417: t047-0771-P-dev4-20261027 version 0.1.0; unvalidated 3.80%
  546. 546 CADGenBench submission origogk_origogk-native-triangle-kernel-diagnosti_20260928-114945: OrigoGK native-triangle kernel diagnostic version 0.1.0; unvalidated 3.77%
  547. 547 CADGenBench submission local-user_t047-0771-p2-dev4-20261027_20261027-034922: t047-0771-P2-dev4-20261027 version 0.1.0; unvalidated 3.72%
  548. 548 CADGenBench submission cadse_qwen3-8-flash-next-local-4-bit-thinking-_20261112-071939: Qwen3.8-Flash-Next (local, 4 bit, thinking on): lean prompt + API idioms + check loop, 9 random fixtures (seed 20261112) version 0.1.0; unvalidated 3.69%
  549. 549 CADGenBench submission cadse_qwen3-8-flash-next-local-4-bit-thinking-_20261112-074554: Qwen3.8-Flash-Next (local, 4 bit, thinking on): principles text + API idioms + check loop, 9 random fixtures (seed 20261112) version 0.1.0; unvalidated 3.60%
  550. 550 CADGenBench submission w1ne_kernelcad-probe-edit-v4-20261020_20261020-013517: kernelcad-probe-edit-v4-20261020 version 0.1.0; unvalidated 3.55%
  551. 551 CADGenBench submission pzfreo_opus5-xhigh-mcp-source-backed-sample6-r1_20260811-100624: opus5-xhigh-mcp-source-backed-sample6-r1 version 0.1.0; unvalidated 3.52%
  552. 552 CADGenBench submission origogk_origogk-surface-bounds-same12-diagnostic_20260928-122509: OrigoGK surface-bounds same12 diagnostic version 0.1.0; unvalidated 3.52%
  553. 553 CADGenBench submission cadse_flash-next-read-sheet-notes-read-then-co_20261112-135102: Flash-Next read + sheet notes: read-then-compare with sheet-metal notes on 108 and 114, 9 random fixtures (seed 20261112) version 0.1.0; unvalidated 3.50%
  554. 554 CADGenBench submission anonymous_anon-edit-1788032760-be22_20260829-194601: anon-edit-1788032760-be22 version 0.1.0; unvalidated 3.48%
  555. 555 CADGenBench submission local-user_t047-r3-p2-r01-20261027_20261027-082316: t047-r3-p2-r01-20261027 version 0.1.0; unvalidated 3.43%
  556. 556 CADGenBench submission cadse_flash-next-lean-r2-qwen3-8-flash-next-on_20261112-135027: Flash-Next lean r2: Qwen3.8-Flash-Next on Brev, thinking on, 12 rounds, 9 random fixtures (seed 20261112) version 0.1.0; unvalidated 3.43%
  557. 557 CADGenBench submission pzfreo_opus5-xhigh-minimal-mcp-cross-sections-s_20260813-051907: opus5-xhigh-minimal-mcp-cross-sections-sample6-r4 version 0.1.0; unvalidated 3.41%
  558. 558 CADGenBench submission cadse_flash-next-read-then-compare-qwen3-8-fla_20261112-134952: Flash-Next read-then-compare: Qwen3.8-Flash-Next on Brev, reads dimensions first and keeps the best-agreeing build, 9 random fixtures (seed 20261112) version 0.1.0; unvalidated 3.35%
  559. 559 CADGenBench submission pzfreo_pzfreo-opus5-xhigh-mcp-fidelity-workflow_20260812-191538: pzfreo-opus5-xhigh-mcp-fidelity-workflow-fe01ca8-sample6-r1 version 0.1.0; unvalidated 3.30%
  560. 560 CADGenBench submission local-user_t047-end-review-a-three-20261030_20261030-043124: t047-end-review-a-three-20261030 version 0.1.0; unvalidated 3.30%
  561. 561 CADGenBench submission anonymous_anon-gen-1788389662-455b_20260902-225424: anon-gen-1788389662-455b version 0.1.0; unvalidated 3.29%
  562. 562 CADGenBench submission anonymous_anon-gen-1788407486-cf7b_20260903-035127: anon-gen-1788407486-cf7b version 0.1.0; unvalidated 3.29%
  563. 563 CADGenBench submission anonymous_run-y_20261112-115942: Run Y version 0.1.0; unvalidated 3.25%
  564. 564 CADGenBench submission anonymous_anon-gen-1788030000-4639_20260829-190002: anon-gen-1788030000-4639 version 0.1.0; unvalidated 3.24%
  565. 565 CADGenBench submission anonymous_ab_20261112-143821: AB version 0.1.0; unvalidated 3.24%
  566. 566 CADGenBench submission yitong42_svga-g-r1-gpt6-svg-gpt56-cad-840e3511902_20260928-042929: SVGA G-r1 GPT6 SVG GPT56 CAD 840e35119023 version 0.1.0; unvalidated 3.19%
  567. 567 CADGenBench submission local-user_t051-r012-c-frozen-followup-20261103_20261103-144030: t051-r012-c-frozen-followup-20261103 version 0.1.0; unvalidated 3.19%
  568. 568 CADGenBench submission anonymous_aa_20261112-135052: AA version 0.1.0; unvalidated 3.19%
  569. 569 CADGenBench submission anonymous_anon-gen-1788486936-fd25_20260904-015537: anon-gen-1788486936-fd25 version 0.1.0; unvalidated 3.14%
  570. 570 CADGenBench submission local-user_t047-tool021-tx-b-20261029_20261029-060423: t047-tool021-tx-b-20261029 version 0.1.0; unvalidated 3.14%
  571. 571 CADGenBench submission anonymous_anon-gen-1788549253-6668_20260904-191414: anon-gen-1788549253-6668 version 0.1.0; unvalidated 3.12%
  572. 572 CADGenBench submission anonymous_anon-gen-1788549393-ab57_20260904-191634: anon-gen-1788549393-ab57 version 0.1.0; unvalidated 3.12%
  573. 573 CADGenBench submission local-user_t051-r010-b2-c_20261102-191249: t051-r010-b2-c version 0.1.0; unvalidated 3.10%
  574. 574 CADGenBench submission yitong42_gpt-6-astra-ultra-svg-gpt-5-6-sol-high-c_20260907-173941: GPT-6 Astra Ultra SVG + GPT-5.6-sol high CAD (4-case) version 0.1.0; unvalidated 3.09%
  575. 575 CADGenBench submission min-liu_chamfer-t2-gen-smoke9_20260709-013720: chamfer-t2-gen-smoke9 version 0.1.0; unvalidated 3.06%
  576. 576 CADGenBench submission pzfreo_opus5-xhigh-mcp-conditional-source-sampl_20260811-160112: opus5-xhigh-mcp-conditional-source-sample6-r1 version 0.1.0; unvalidated 3.06%
  577. 577 CADGenBench submission local-user_t051-r004-c_20261102-022312: t051-r004-c version 0.1.0; unvalidated 3.03%
  578. 578 CADGenBench submission local-user_t051-r004-c-infra-retry1_20261102-040853: t051-r004-c-infra-retry1 version 0.1.0; unvalidated 3.03%
  579. 579 CADGenBench submission min-liu_cad-agent-probe-fusion-360-mcp-x-claude-_20260704-232309: cad-agent probe (Fusion 360 MCP x Claude Opus, fixtures 101-108) version 0.1.0; unvalidated 2.98%
  580. 580 CADGenBench submission yitong42_svga-g-r2-gpt6-svg-gpt56-cad-840e3511902_20260928-042939: SVGA G-r2 GPT6 SVG GPT56 CAD 840e35119023 version 0.1.0; unvalidated 2.96%
  581. 581 CADGenBench submission cad-mcp-research_inspection-first-comparison-cell-0746582_20260824-054050: inspection-first comparison cell-074658225db50681b737 version 0.1.0; unvalidated 2.95%
  582. 582 CADGenBench submission anonymous_run-x_20261112-115818: Run X version 0.1.0; unvalidated 2.94%
  583. 583 CADGenBench submission local-user_t051-r010-b2-b_20261102-194032: t051-r010-b2-b version 0.1.0; unvalidated 2.93%
  584. 584 CADGenBench submission local-user_t047-772-fresh-three-a-20261031_20261030-174933: t047-772-fresh-three-a-20261031 version 0.1.0; unvalidated 2.92%
  585. 585 CADGenBench submission local-user_t051-r005-c_20261102-061259: t051-r005-c version 0.1.0; unvalidated 2.90%
  586. 586 CADGenBench submission local-user_t051-r010-b1-c_20261102-184255: t051-r010-b1-c version 0.1.0; unvalidated 2.90%
  587. 587 CADGenBench submission yitong42_svgq-a-r1-gpt56-high-618c9855edcd_20260927-191017: SVGQ A-r1 GPT56 high 618c9855edcd version 0.1.0; unvalidated 2.88%
  588. 588 CADGenBench submission local-user_t051-r010-b1-a_20261102-185031: t051-r010-b1-a version 0.1.0; unvalidated 2.86%
  589. 589 CADGenBench submission local-user_t051-r010-b2-a_20261102-192434: t051-r010-b2-a version 0.1.0; unvalidated 2.86%
  590. 590 CADGenBench submission anonymous_run-z_20261112-125840: Run Z version 0.1.0; unvalidated 2.86%
  591. 591 CADGenBench submission cad-mcp-research_inspection-first-comparison-cell-4c0ea99_20260824-055326: inspection-first comparison cell-4c0ea99f1d39970c13cd version 0.1.0; unvalidated 2.85%
  592. 592 CADGenBench submission local-user_t047-cvd1-t-20261028_20261028-094744: t047-cvd1-t-20261028 version 0.1.0; unvalidated 2.83%
  593. 593 CADGenBench submission cad-mcp-research_inspection-first-comparison-cell-630b5e0_20260824-055912: inspection-first comparison cell-630b5e09508b67f40702 version 0.1.0; unvalidated 2.81%
  594. 594 CADGenBench submission cad-mcp-research_inspection-first-comparison-cell-bb69143_20260824-061044: inspection-first comparison cell-bb691437fd2c19f879ed version 0.1.0; unvalidated 2.80%
  595. 595 CADGenBench submission local-user_t051-r010-b1-ab_20261102-190514: t051-r010-b1-ab version 0.1.0; unvalidated 2.79%
  596. 596 CADGenBench submission local-user_t047-cvd1-c-20261028_20261028-094122: t047-cvd1-c-20261028 version 0.1.0; unvalidated 2.77%
  597. 597 CADGenBench submission pzfreo_fable5-v0360-xhigh-smoke3_20260701-221618: fable5-v0360-xhigh-SMOKE3 version 0.1.0; unvalidated 2.76%
  598. 598 CADGenBench submission lehuili_gpt5-6-atomic-reflect-2d_20260909-042736: gpt5.6-atomic-reflect-2D version 0.1.0; unvalidated 2.76%
  599. 599 CADGenBench submission cad-mcp-research_inspection-first-development-cell-02cf3d_20260823-002431: inspection-first development cell-02cf3d0c30148c2ed1a1 version 0.1.0; unvalidated 2.74%
  600. 600 CADGenBench submission yitong42_matched-baseline-codex-gpt-5-6-sol-high-_20260907-092712: Matched baseline + Codex gpt-5.6-sol high (semantic-v1, 4-case) version 0.1.0; unvalidated 2.71%
  601. 601 CADGenBench submission yitong42_svgq-d-r2-gpt56-high-618c9855edcd_20260927-191631: SVGQ D-r2 GPT56 high 618c9855edcd version 0.1.0; unvalidated 2.71%
  602. 602 CADGenBench submission anonymous_anon-gen-1787960079-6878_20260828-233440: anon-gen-1787960079-6878 version 0.1.0; unvalidated 2.66%
  603. 603 CADGenBench submission anonymous_anon-gen-1787960533-2534_20260828-234214: anon-gen-1787960533-2534 version 0.1.0; unvalidated 2.66%
  604. 604 CADGenBench submission cad-mcp-research_inspection-first-development-cell-a60fbd_20260823-014644: inspection-first development cell-a60fbdf6db6c69ed6e10 version 0.1.0; unvalidated 2.65%
  605. 605 CADGenBench submission yitong42_svgq-c-r1-gpt56-high-618c9855edcd_20260927-191400: SVGQ C-r1 GPT56 high 618c9855edcd version 0.1.0; unvalidated 2.63%
  606. 606 CADGenBench submission reify_reify-deepseek-low-naked-211-215-config-_20261022-061630: reify-deepseek-low-naked-211-215-config-01 version 0.1.0; unvalidated 2.62%
  607. 607 CADGenBench submission anon-190312_sweep-d3_20260910-205325: sweep-d3 version 0.1.0; unvalidated 2.61%
  608. 608 CADGenBench submission local-user_t051-r007-t_20261102-085108: t051-r007-t version 0.1.0; unvalidated 2.61%
  609. 609 CADGenBench submission local-user_t051-r006-t_20261102-080915: t051-r006-t version 0.1.0; unvalidated 2.60%
  610. 610 CADGenBench submission yitong42_m2d-first-codex-gpt-5-6-sol-high-semanti_20260907-093502: M2D-first + Codex gpt-5.6-sol high (semantic-v1, 4-case) version 0.1.0; unvalidated 2.59%
  611. 611 CADGenBench submission local-user_t051-r008-t_20261102-094036: t051-r008-t version 0.1.0; unvalidated 2.58%
  612. 612 CADGenBench submission yitong42_oldprompt-paired-baseline-gpt-5-6-sol-hi_20260914-152659: OldPrompt paired baseline GPT-5.6-sol high 4-case 20260914-191500 version 0.1.0; unvalidated 2.57%
  613. 613 CADGenBench submission cad-mcp-research_inspection-first-development-cell-0af180_20260823-003654: inspection-first development cell-0af180ba59a5f3524569 version 0.1.0; unvalidated 2.55%
  614. 614 CADGenBench submission yitong42_metric-m-r1-gpt56-metric-first-svg-cad-e_20260929-090822: METRIC M-r1 GPT56 metric-first SVG CAD ef73db60fade version 0.1.0; unvalidated 2.55%
  615. 615 CADGenBench submission cad-mcp-research_inspection-first-development-cell-141a78_20260823-004305: inspection-first development cell-141a781f828c31cd9c2a version 0.1.0; unvalidated 2.53%
  616. 616 CADGenBench submission yitong42_oldprompt-paired-svg-first-gpt-5-6-sol-h_20260914-152659: OldPrompt paired svg-first GPT-5.6-sol high 4-case 20260914-191500 version 0.1.0; unvalidated 2.53%
  617. 617 CADGenBench submission pzfreo_gpt55-v0364-xhigh-unstepped-retest_20260704-065437: gpt55-v0364-xhigh-unstepped-retest version 0.1.0; unvalidated 2.52%
  618. 618 CADGenBench submission local-user_t051-r010-b2-ab_20261102-194913: t051-r010-b2-ab version 0.1.0; unvalidated 2.52%
  619. 619 CADGenBench submission cad-mcp-research_inspection-first-development-cell-89a36d_20260823-013213: inspection-first development cell-89a36dbcaa2ca924fba8 version 0.1.0; unvalidated 2.51%
  620. 620 CADGenBench submission yitong42_svgq-b-r1-gpt56-high-618c9855edcd_20260927-191216: SVGQ B-r1 GPT56 high 618c9855edcd version 0.1.0; unvalidated 2.51%
  621. 621 CADGenBench submission cad-mcp-research_inspection-first-development-cell-76a8b5_20260823-011808: inspection-first development cell-76a8b51ed947e4d1e963 version 0.1.0; unvalidated 2.50%
  622. 622 CADGenBench submission yitong42_paired-baseline-gpt-5-6-sol-high-4-case-_20260914-100552: Paired baseline GPT-5.6-sol high 4-case 20260914-154500 version 0.1.0; unvalidated 2.49%
  623. 623 CADGenBench submission local-user_t047-0773-feedback-a-20261101_20261101-030942: t047-0773-feedback-a-20261101 version 0.1.0; unvalidated 2.48%
  624. 624 CADGenBench submission yitong42_svgq-b-r2-gpt56-high-618c9855edcd_20260927-191308: SVGQ B-r2 GPT56 high 618c9855edcd version 0.1.0; unvalidated 2.47%
  625. 625 CADGenBench submission yitong42_svgq-c-r2-gpt56-high-618c9855edcd_20260927-191451: SVGQ C-r2 GPT56 high 618c9855edcd version 0.1.0; unvalidated 2.47%
  626. 626 CADGenBench submission pzfreo_gpt55-v0373-smoke5_20260708-102200: gpt55-v0373-smoke5 version 0.1.0; unvalidated 2.45%
  627. 627 CADGenBench submission cad-mcp-research_inspection-first-development-cell-fbc1fc_20260823-015341: inspection-first development cell-fbc1fc0ce6dc251d5efc version 0.1.0; unvalidated 2.45%
  628. 628 CADGenBench submission yitong42_paired-svg-first-gpt-5-6-sol-high-4-case_20260914-100759: Paired svg-first GPT-5.6-sol high 4-case 20260914-154500 version 0.1.0; unvalidated 2.45%
  629. 629 CADGenBench submission local-user_gemini38-0773-baseline-20261103-fixturef_20261103-031745: gemini38-0773-baseline-20261103-fixturefix1 version 0.1.0; unvalidated 2.45%
  630. 630 CADGenBench submission cad-mcp-research_inspection-first-development-cell-067743_20260823-003051: inspection-first development cell-0677434281d885366a2f version 0.1.0; unvalidated 2.44%
  631. 631 CADGenBench submission cad-mcp-research_inspection-first-development-cell-fbe5f2_20260823-015910: inspection-first development cell-fbe5f2475be209c783a8 version 0.1.0; unvalidated 2.43%
  632. 632 CADGenBench submission yitong42_metric-m-r2-gpt56-metric-first-svg-cad-e_20260929-090912: METRIC M-r2 GPT56 metric-first SVG CAD ef73db60fade version 0.1.0; unvalidated 2.43%
  633. 633 CADGenBench submission niming_a-research_20261002-075325: a_research version 0.1.0; unvalidated 2.41%
  634. 634 CADGenBench submission local-user_t051-r004-t_20261102-022533: t051-r004-t version 0.1.0; unvalidated 2.41%
  635. 635 CADGenBench submission local-user_t051-r004-t-infra-retry1_20261102-041126: t051-r004-t-infra-retry1 version 0.1.0; unvalidated 2.41%
  636. 636 CADGenBench submission one-research_gpt-5-6-sol-v9-step-r3-101-102-103-128_20260913-135427: GPT-5.6-sol-v9-step-r3-101-102-103-128 version 0.1.0; unvalidated 2.40%
  637. 637 CADGenBench submission cad-mcp-research_inspection-first-development-cell-6415c0_20260823-010753: inspection-first development cell-6415c0063e381291cecd version 0.1.0; unvalidated 2.39%
  638. 638 CADGenBench submission yitong42_direct-svg-first-codex-gpt-5-6-sol-high-_20260907-134035: Direct SVG-first + Codex gpt-5.6-sol high (svg-v2, 4-case) version 0.1.0; unvalidated 2.39%
  639. 639 CADGenBench submission local-user_t051-r001-d02_20261101-080615: t051-r001-d02 version 0.1.0; unvalidated 2.39%
  640. 640 CADGenBench submission wolf_pi-agent-4cases-step_20260908-083822: pi-agent-4cases-step version 0.1.0; unvalidated 2.38%
  641. 641 CADGenBench submission local-user_t051-r006-c_20261102-080053: t051-r006-c version 0.1.0; unvalidated 2.38%
  642. 642 CADGenBench submission yitong42_svgq-a-r2-gpt56-high-618c9855edcd_20260927-191126: SVGQ A-r2 GPT56 high 618c9855edcd version 0.1.0; unvalidated 2.36%
  643. 643 CADGenBench submission local-user_t047-d1-a-r02-20261027_20261027-162331: t047-d1-a-r02-20261027 version 0.1.0; unvalidated 2.36%
  644. 644 CADGenBench submission gkgyc233_a-test-of-one-sample-on-gpt-6-astra_20260912-103520: A test of one sample on GPT 6 Astra version 0.1.0; unvalidated 2.35%
  645. 645 CADGenBench submission local-user_t047-d1-b-r01-20261027_20261027-163207: t047-d1-b-r01-20261027 version 0.1.0; unvalidated 2.34%
  646. 646 CADGenBench submission local-user_t047-d1-b-r02-20261027_20261027-162745: t047-d1-b-r02-20261027 version 0.1.0; unvalidated 2.34%
  647. 647 CADGenBench submission cad-mcp-research_inspection-first-development-cell-7eb40f_20260823-012428: inspection-first development cell-7eb40ff4e913fca57016 version 0.1.0; unvalidated 2.31%
  648. 648 CADGenBench submission local-user_t051-r001-c_20261101-080327: t051-r001-c version 0.1.0; unvalidated 2.31%
  649. 649 CADGenBench submission local-user_t051-r001-d03_20261101-080656: t051-r001-d03 version 0.1.0; unvalidated 2.31%
  650. 650 CADGenBench submission yitong42_autonomous-svg-codex-gpt-5-6-sol-high-ca_20260908-062724: Autonomous SVG + Codex GPT-5.6-sol high CAD (4-case) version 0.1.0; unvalidated 2.30%
  651. 651 CADGenBench submission marzipan_marzipan_20260910-003143: marzipan version 0.1.0; unvalidated 2.29%
  652. 652 CADGenBench submission w1ne_kernelcad-probe-gen-20261019_20261019-184630: kernelcad-probe-gen-20261019 version 0.1.0; unvalidated 2.27%
  653. 653 CADGenBench submission cad-mcp-research_inspection-first-development-cell-00372f_20260823-001706: inspection-first development cell-00372fd9856d4285f61b version 0.1.0; unvalidated 2.26%
  654. 654 CADGenBench submission yitong42_svgq-d-r1-gpt56-high-618c9855edcd_20260927-191541: SVGQ D-r1 GPT56 high 618c9855edcd version 0.1.0; unvalidated 2.26%
  655. 655 CADGenBench submission cad-mcp-research_inspection-first-development-cell-94b7ca_20260823-014156: inspection-first development cell-94b7ca74fcea622f3cac version 0.1.0; unvalidated 2.22%
  656. 656 CADGenBench submission arisa_gpt-5-6-sol-step-wise-strategy-v1-r2-101_20260914-114547: GPT-5.6-sol-step-wise-strategy-v1-r2-101-102-103-128 version 0.1.0; unvalidated 2.21%
  657. 657 CADGenBench submission local-user_t051-r001-d01_20261101-080528: t051-r001-d01 version 0.1.0; unvalidated 2.20%
  658. 658 CADGenBench submission cad-mcp-research_inspection-first-development-cell-1e4c04_20260823-005013: inspection-first development cell-1e4c046ffffb40877352 version 0.1.0; unvalidated 2.19%
  659. 659 CADGenBench submission cad-mcp-research_inspection-first-development-cell-357d7d_20260823-005637: inspection-first development cell-357d7d06dcbee1ede716 version 0.1.0; unvalidated 2.19%
  660. 660 CADGenBench submission local-user_t047-772-feedback-repair-two-20261030_20261030-160122: t047-772-feedback-repair-two-20261030 version 0.1.0; unvalidated 2.19%
  661. 661 CADGenBench submission local-user_t047-0773-feedback-b-20261101_20261101-034711: t047-0773-feedback-b-20261101 version 0.1.0; unvalidated 2.17%
  662. 662 CADGenBench submission anonymous_anon-gen-1787959342-3f06_20260828-232223: anon-gen-1787959342-3f06 version 0.1.0; unvalidated 2.16%
  663. 663 CADGenBench submission yitong42_m2d-first-codex-gpt-5-6-sol-high-4-case-_20260906-070144: M2D-first + Codex gpt-5.6-sol high (4-case, 20260906) version 0.1.0; unvalidated 2.16%
  664. 664 CADGenBench submission local-user_t051-r009-t_20261102-131444: t051-r009-t version 0.1.0; unvalidated 2.15%
  665. 665 CADGenBench submission local-user_t051-r007-c_20261102-084233: t051-r007-c version 0.1.0; unvalidated 2.14%
  666. 666 CADGenBench submission lehuili_gpt-5-6-sol-self-reflect-2d-inspect-4-ca_20260822-071528: GPT-5.6 Sol Self Reflect + 2D Inspect (4-case) version 0.1.0; unvalidated 2.13%
  667. 667 CADGenBench submission cad-edit_edit-5-sample-run_20261011-125812: edit-5-sample-run version 0.1.0; unvalidated 2.13%
  668. 668 CADGenBench submission local-user_t051-r005-t_20261102-063046: t051-r005-t version 0.1.0; unvalidated 2.13%
  669. 669 CADGenBench submission local-user_t051-r009-c_20261102-130716: t051-r009-c version 0.1.0; unvalidated 2.13%
  670. 670 CADGenBench submission anonymous_ac_20261112-154838: AC version 0.1.0; unvalidated 2.11%
  671. 671 CADGenBench submission anonymous_ac_20261112-160639: AC version 0.1.0; unvalidated 2.11%
  672. 672 CADGenBench submission cad-mcp-research_inspection-first-comparison-cell-90ac68c_20260824-060431: inspection-first comparison cell-90ac68cb965dd8f90995 version 0.1.0; unvalidated 2.06%
  673. 673 CADGenBench submission local-user_t047-tool021-diag-t-r1-20261029_20261029-024855: t047-tool021-diag-t-r1-20261029 version 0.1.0; unvalidated 2.04%
  674. 674 CADGenBench submission lehuili_gpt-5-6-sol-self-reflect-second-pass-4-c_20260821-152311: GPT-5.6 Sol Self Reflect Second Pass (4-case) version 0.1.0; unvalidated 2.03%
  675. 675 CADGenBench submission arisa_gpt-5-6-sol-step-wise-strategy-v1-r1-101_20260914-114510: GPT-5.6-sol-step-wise-strategy-v1-r1-101-102-103-128 version 0.1.0; unvalidated 2.03%
  676. 676 CADGenBench submission local-user_t047-tool021-diag-c-r1-20261029_20261029-024716: t047-tool021-diag-c-r1-20261029 version 0.1.0; unvalidated 2.02%
  677. 677 CADGenBench submission local-user_t047-772-fresh-three-b-20261031_20261030-175017: t047-772-fresh-three-b-20261031 version 0.1.0; unvalidated 2.02%
  678. 678 CADGenBench submission lehuili_gpt-5-6-sol-self-reflect-2d-inspect-same_20260822-083539: GPT-5.6 Sol Self Reflect + 2D Inspect Same-Region Closure (4-case) version 0.1.0; unvalidated 2.01%
  679. 679 CADGenBench submission lehuili_gpt-5-6-sol-two-stage-reflection-post-ed_20260822-092931: GPT-5.6 Sol Two-Stage Reflection + Post-Edit Acceptance Closed Loop (4-case) version 0.1.0; unvalidated 2.00%
  680. 680 CADGenBench submission wolf_pi-agent-4cases_20260908-083746: pi-agent-4cases version 0.1.0; unvalidated 2.00%
  681. 681 CADGenBench submission arisa_gpt-5-6-sol-step-wise-strategy-v1-r3-101_20260914-114625: GPT-5.6-sol-step-wise-strategy-v1-r3-101-102-103-128 version 0.1.0; unvalidated 1.99%
  682. 682 CADGenBench submission cad-edit-test_test-5-samples_20261011-103623: test-5-samples version 0.1.0; unvalidated 1.99%
  683. 683 CADGenBench submission lehuili_gpt-5-6-sol-main-agent-self-reflect-4-ca_20260821-122617: GPT-5.6 Sol Main Agent Self Reflect (4-case) version 0.1.0; unvalidated 1.98%
  684. 684 CADGenBench submission cad-mcp-research_inspection-first-development-cell-5019c5_20260823-010251: inspection-first development cell-5019c5b12d6b90ed5ca4 version 0.1.0; unvalidated 1.97%
  685. 685 CADGenBench submission anonymous_anon-gen-1787964075-a10f_20260829-004116: anon-gen-1787964075-a10f version 0.1.0; unvalidated 1.97%
  686. 686 CADGenBench submission anonymous_anon-gen-1787968204-52a0_20260829-015005: anon-gen-1787968204-52a0 version 0.1.0; unvalidated 1.97%
  687. 687 CADGenBench submission yitong42_matched-baseline-codex-gpt-5-6-sol-high-_20260906-112731: Matched baseline + Codex gpt-5.6-sol high (4-case) version 0.1.0; unvalidated 1.97%
  688. 688 CADGenBench submission one-research_gpt-5-6-sol-v9-pi-agent-r3-101-102-103-1_20260913-135330: GPT-5.6-sol-v9-pi-agent-r3-101-102-103-128 version 0.1.0; unvalidated 1.95%
  689. 689 CADGenBench submission cad-mcp-research_inspection-first-comparison-cell-4519f7a_20260824-054754: inspection-first comparison cell-4519f7a9003e08c7496f version 0.1.0; unvalidated 1.94%
  690. 690 CADGenBench submission one-research_gpt-5-6-sol-no-steps_20260910-113355: GPT-5.6-sol-no_steps version 0.1.0; unvalidated 1.94%
  691. 691 CADGenBench submission pzfreo_opus5-xhigh-direct-build123d-nomcp-pilot_20260809-174214: opus5-xhigh-direct-build123d-nomcp-pilot2-partial version 0.1.0; unvalidated 1.93%
  692. 692 CADGenBench submission anonymous_anon-gen-1788135167-b8ef_20260831-001249: anon-gen-1788135167-b8ef version 0.1.0; unvalidated 1.93%
  693. 693 CADGenBench submission one-research_gpt-5-6-sol-steps-rerun_20260910-145136: GPT-5.6-sol-steps-rerun version 0.1.0; unvalidated 1.93%
  694. 694 CADGenBench submission lehuili_gpt-5-6-sol-view-search-dual-roi-reflect_20260821-122637: GPT-5.6 Sol View Search + Dual-ROI Reflection (4-case) version 0.1.0; unvalidated 1.92%
  695. 695 CADGenBench submission cad-mcp-research_inspection-first-development-cell-6a3b89_20260823-011256: inspection-first development cell-6a3b898bb8fa83f8fb18 version 0.1.0; unvalidated 1.92%
  696. 696 CADGenBench submission one-research_gpt-5-6-sol-steps_20260910-113415: GPT-5.6-sol-steps version 0.1.0; unvalidated 1.92%
  697. 697 CADGenBench submission pzfreo_gpt55-v0372-smoke5_20260707-195934: gpt55-v0372-smoke5 version 0.1.0; unvalidated 1.91%
  698. 698 CADGenBench submission pzfreo_gpt55-v0372-smoke5-r2_20260707-203158: gpt55-v0372-smoke5-r2 version 0.1.0; unvalidated 1.91%
  699. 699 CADGenBench submission one-research_gpt-5-6-sol-v9-pi-agent-r1-101-102-103-1_20260913-134652: GPT-5.6-sol-v9-pi-agent-r1-101-102-103-128 version 0.1.0; unvalidated 1.90%
  700. 700 CADGenBench submission lehuili_gpt-5-6-sol-self-reflect-two-stage-refle_20260821-155434: GPT-5.6 Sol Self Reflect + Two-Stage Reflection (4-case) version 0.1.0; unvalidated 1.87%
  701. 701 CADGenBench submission lehuili_gpt-5-6-sol-view-search-no-crop-reflecti_20260821-122543: GPT-5.6 Sol View Search + No-Crop Reflection (4-case) version 0.1.0; unvalidated 1.87%
  702. 702 CADGenBench submission one-research_gpt-5-6-sol-v9-step-r1-101-102-103-128_20260913-135351: GPT-5.6-sol-v9-step-r1-101-102-103-128 version 0.1.0; unvalidated 1.86%
  703. 703 CADGenBench submission local-user_t047-m1x1-t-20261028_20261028-054234: t047-m1x1-t-20261028 version 0.1.0; unvalidated 1.85%
  704. 704 CADGenBench submission yitong42_svg-first-codex-gpt-5-6-sol-high-4-case-_20260905-102720: SVG-first Codex + gpt-5.6-sol high (4-case diagnostic) version 0.1.0; unvalidated 1.84%
  705. 705 CADGenBench submission lehuili_gpt-5-6-sol-main-agent-direct-4-case_20260821-122554: GPT-5.6 Sol Main Agent Direct (4-case) version 0.1.0; unvalidated 1.83%
  706. 706 CADGenBench submission lehuili_gpt-5-6-sol-main-agent-fixed-view-2d-sel_20260821-162630: GPT-5.6 Sol Main Agent Fixed-View 2D Self-Reflection (4-case) version 0.1.0; unvalidated 1.81%
  707. 707 CADGenBench submission lehuili_gpt-5-6-sol-atomic-geometry-repair-4-cas_20260908-162606: GPT-5.6 Sol Atomic Geometry Repair (4-case, 2026-09-08) version 0.1.0; unvalidated 1.80%
  708. 708 CADGenBench submission one-research_gpt-5-6-sol-v9-pi-agent-r2-101-102-103-1_20260913-135255: GPT-5.6-sol-v9-pi-agent-r2-101-102-103-128 version 0.1.0; unvalidated 1.79%
  709. 709 CADGenBench submission local-user_t047-r3-p2-r02-20261027_20261027-082405: t047-r3-p2-r02-20261027 version 0.1.0; unvalidated 1.78%
  710. 710 CADGenBench submission anonymous_cadgenbench-111-148-test-2_20260905-132001: CADGenBench 111+148 test 2 version 0.1.0; unvalidated 1.77%
  711. 711 CADGenBench submission one-research_gpt-5-6-sol-no-steps-rerun_20260910-145542: GPT-5.6-sol-no_steps-rerun version 0.1.0; unvalidated 1.77%
  712. 712 CADGenBench submission local-user_t047-r3-b-r03-20261027_20261027-082224: t047-r3-b-r03-20261027 version 0.1.0; unvalidated 1.74%
  713. 713 CADGenBench submission local-user_t051-r010-b1-b_20261102-185656: t051-r010-b1-b version 0.1.0; unvalidated 1.74%
  714. 714 CADGenBench submission anonymous_h45-a1-partial_20261021-111114: H45-A1 (partial) version 0.1.0; unvalidated 1.72%
  715. 715 CADGenBench submission local-user_t047-r3-b-r02-20261027_20261027-082132: t047-r3-b-r02-20261027 version 0.1.0; unvalidated 1.72%
  716. 716 CADGenBench submission numafi-7095_gen2-numafi-7095_20261102-203546: gen2-numafi-7095 version 0.1.0; unvalidated 1.72%
  717. 717 CADGenBench submission local-user_t047-tool021-diag-t-r2-20261029_20261029-025013: t047-tool021-diag-t-r2-20261029 version 0.1.0; unvalidated 1.71%
  718. 718 CADGenBench submission local-user_t047-r3-p2-r03-20261027_20261027-082506: t047-r3-p2-r03-20261027 version 0.1.0; unvalidated 1.70%
  719. 719 CADGenBench submission local-user_t051-r008-c_20261102-092933: t051-r008-c version 0.1.0; unvalidated 1.70%
  720. 720 CADGenBench submission one-research_gpt-5-6-sol-v9-step-r2-101-102-103-128_20260913-135407: GPT-5.6-sol-v9-step-r2-101-102-103-128 version 0.1.0; unvalidated 1.69%
  721. 721 CADGenBench submission lehuili_gpt-5-6-sol-main-edit-preview-4-case-202_20260909-030433: GPT-5.6 Sol Main Edit Preview (4-case, 2026-09-09) version 0.1.0; unvalidated 1.68%
  722. 722 CADGenBench submission local-user_t047-m1x1-c-20261028_20261028-054131: t047-m1x1-c-20261028 version 0.1.0; unvalidated 1.68%
  723. 723 CADGenBench submission cad-mcp-research_inspection-first-development-cell-8b3b68_20260823-013718: inspection-first development cell-8b3b6875fd8deb1620d0 version 0.1.0; unvalidated 1.66%
  724. 724 CADGenBench submission cadgenbench-reflection-study_pi-kimi-k3-reflection-after-102-103-145_20260815-104735: Pi Kimi K3 Reflection AFTER 102 103 145 version 0.1.0; unvalidated 1.65%
  725. 725 CADGenBench submission cadgenbench-reflection-study_pi-kimi-k3-incremental-editable-reflecti_20260816-202605: Pi Kimi K3 Incremental Editable Reflection Guided 102 103 145 version 0.1.0; unvalidated 1.63%
  726. 726 CADGenBench submission local-user_t047-d1-a-r01-20261027_20261027-162140: t047-d1-a-r01-20261027 version 0.1.0; unvalidated 1.62%
  727. 727 CADGenBench submission cadgenbench-reflection-study_pi-kimi-k3-post-submit-dual-roi-reflecti_20260817-033318: Pi Kimi K3 Post-Submit Dual ROI Reflection Guided 102 103 145 version 0.1.0; unvalidated 1.61%
  728. 728 CADGenBench submission lehuili_gpt-5-6-sol-optional-reflect-causal-repa_20260822-145641: GPT-5.6 Sol Optional Reflect + Causal Repair (4-case) version 0.1.0; unvalidated 1.60%
  729. 729 CADGenBench submission local-user_t047-d2g-d3e-c-r01-20261028_20261028-014901: t047-d2g-d3e-c-r01-20261028 version 0.1.0; unvalidated 1.60%
  730. 730 CADGenBench submission local-user_t047-d2g-d3e-c-r02-20261028_20261028-015028: t047-d2g-d3e-c-r02-20261028 version 0.1.0; unvalidated 1.60%
  731. 731 CADGenBench submission local-user_t047-d2g-d3e-t-r01-20261028_20261028-015139: t047-d2g-d3e-t-r01-20261028 version 0.1.0; unvalidated 1.60%
  732. 732 CADGenBench submission local-user_t047-d2g-d3e-t-r02-20261028_20261028-015222: t047-d2g-d3e-t-r02-20261028 version 0.1.0; unvalidated 1.60%
  733. 733 CADGenBench submission cadgenbench-reflection-study_pi-kimi-k3-dual-roi-reflection-guided-10_20260816-151158: Pi Kimi K3 Dual ROI Reflection Guided 102 103 145 version 0.1.0; unvalidated 1.59%
  734. 734 CADGenBench submission anonymous_anon-gen-1788070413-8f87_20260830-061334: anon-gen-1788070413-8f87 version 0.1.0; unvalidated 1.56%
  735. 735 CADGenBench submission lindacyffan_pi-agent-qwen3-8-steps-101-103-118_20260906-144933: Pi Agent - Qwen3.8-steps- 101+103+118 version 0.1.0; unvalidated 1.54%
  736. 736 CADGenBench submission cadgenbench-reflection-study_pi-kimi-k3-verified-dual-roi-reflection-_20260816-175950: Pi Kimi K3 Verified Dual ROI Reflection Guided 102 103 145 version 0.1.0; unvalidated 1.53%
  737. 737 CADGenBench submission anonymous_anon-edit-1787967797-0357_20260829-014318: anon-edit-1787967797-0357 version 0.1.0; unvalidated 1.53%
  738. 738 CADGenBench submission paramancer_paramancer-build123d-mcp-0-3-85-dev0-gpt_20261017-123044: paramancer-build123d-mcp-0.3.85.dev0-gpt-6.1-sol-high-pilot-20261017 version 0.1.0; unvalidated 1.52%
  739. 739 CADGenBench submission yitong42_codex-gpt-5-6-sol-high-4-case-baseline_20260905-104105: Codex + gpt-5.6-sol high (4-case baseline) version 0.1.0; unvalidated 1.47%
  740. 740 CADGenBench submission cadgenbench-reflection-study_pi-kimi-k3-reflection-before-102-103-145_20260815-104640: Pi Kimi K3 Reflection BEFORE 102 103 145 version 0.1.0; unvalidated 1.44%
  741. 741 CADGenBench submission cadgenbench-reflection-study_pi-kimi-k3-optional-dual-roi-reflection-_20260816-143854: Pi Kimi K3 Optional Dual ROI Reflection 102 103 145 version 0.1.0; unvalidated 1.44%
  742. 742 CADGenBench submission reify_reify-gpt-6-1-sol-low-101-201-pilot_20261021-080035: Reify GPT-6.1 Sol low - 101 201 pilot version 0.1.0; unvalidated 1.42%
  743. 743 CADGenBench submission zky_pi-agent-glm-5-3-flash-fixtures-101-102-_20260902-034512: Pi Agent GLM-5.3-Flash fixtures 101-102-103-111 version 0.1.0; unvalidated 1.41%
  744. 744 CADGenBench submission lindacyffan_pi-agent-qwen3-8-101-103-118_20260906-144715: Pi Agent - Qwen3.8- 101+103+118 version 0.1.0; unvalidated 1.41%
  745. 745 CADGenBench submission anonymous_anon-edit-1787966903-ab75_20260829-012824: anon-edit-1787966903-ab75 version 0.1.0; unvalidated 1.38%
  746. 746 CADGenBench submission reify-evaluation_reify-0-1-1-gpt-5-6-sol-medium-hardest10_20261012-043910: Reify 0.1.1 gpt-5.6-sol medium hardest10 partial3 20261011 version 0.1.0; unvalidated 1.37%
  747. 747 CADGenBench submission cadgenbench-reflection-study_pi-kimi-k3-main-agent-self-reflect-102-1_20260815-142707: Pi Kimi K3 Main Agent Self Reflect 102 103 145 version 0.1.0; unvalidated 1.36%
  748. 748 CADGenBench submission cadgenbench-reflection-study_pi-kimi-k3-fixed-grid-reflection-guided-_20260816-222358: Pi Kimi K3 Fixed Grid Reflection Guided 102 103 145 version 0.1.0; unvalidated 1.33%
  749. 749 CADGenBench submission verdigris_verdigris_20260909-221559: verdigris version 0.1.0; unvalidated 1.28%
  750. 750 CADGenBench submission local-user_t047-tool021-diag-c-r2-20261029_20261029-024933: t047-tool021-diag-c-r2-20261029 version 0.1.0; unvalidated 1.26%
  751. 751 CADGenBench submission zky_pi-agent-steps-qwen3-8-103-118_20260906-044155: Pi Agent + steps - Qwen3.8-103 + 118 version 0.1.0; unvalidated 1.22%
  752. 752 CADGenBench submission arisa_gpt-5-6-sol-step-wise-strategy-v1-increm_20260915-053748: GPT-5.6-sol-step-wise-strategy-v1-incremental-visual-check-r1-102-103 version 0.1.0; unvalidated 1.22%
  753. 753 CADGenBench submission gkgyc233_a-test-of-one-sample-on-gpt-6-astra_20260907-113058: A test of one sample on GPT 6 Astra version 0.1.0; unvalidated 1.21%
  754. 754 CADGenBench submission anonymous_anon-edit-1788298205-22f6_20260901-213006: anon-edit-1788298205-22f6 version 0.1.0; unvalidated 1.20%
  755. 755 CADGenBench submission anonymous_anon-gen-1788803033-562e4d_20260907-174354: anon-gen-1788803033-562e4d version 0.1.0; unvalidated 1.20%
  756. 756 CADGenBench submission lindacyffan_pi-agent-qwen3-8-115-128_20260907-045804: Pi Agent - Qwen3.8-115+128 version 0.1.0; unvalidated 1.20%
  757. 757 CADGenBench submission anonymous_anon-gen-1789083011-74e9e3_20260911-010046: anon-gen-1789083011-74e9e3 version 0.1.0; unvalidated 1.20%
  758. 758 CADGenBench submission reify-evaluation_reify-user-rerun-hardest10-203-20261012_20261012-045422: Reify user rerun hardest10 203 20261012 version 0.1.0; unvalidated 1.20%
  759. 759 CADGenBench submission wolf_cadgenresearchs-102-103_20260907-110054: CADgenResearchs-102+103 version 0.1.0; unvalidated 1.19%
  760. 760 CADGenBench submission zky_pi-agent-qwen3-8-103-118_20260906-042924: Pi Agent Qwen3.8-103 + 118 version 0.1.0; unvalidated 1.18%
  761. 761 CADGenBench submission yitong42_pi-agent-gpt-5-6-sol-high-3-sample-diagn_20260808-093153: Pi Agent + gpt-5.6-sol high (3-sample diagnostic) version 0.1.0; unvalidated 1.17%
  762. 762 CADGenBench submission zky_pi-agent-glm-5-3-flash-fixtures-101-102-_20260902-023005: Pi Agent GLM-5.3-Flash fixtures 101-102-111 version 0.1.0; unvalidated 1.17%
  763. 763 CADGenBench submission yitong42_codex-gpt-6-astra-ultra-baseline-case-10_20260906-160657: Codex GPT-6 Astra Ultra baseline (case 102) version 0.1.0; unvalidated 1.17%
  764. 764 CADGenBench submission cadse_gemma-4-e4b-local-4b-drawing-api-idioms-_20261112-093017: Gemma-4-E4B (local, 4B): drawing + API idioms + check loop, first valid of three arms per part, 9 random fixtures (seed 20261112) version 0.1.0; unvalidated 1.17%
  765. 765 CADGenBench submission jake-fitzgerald_codex-build123d-first3-validation_20260609-112054: Codex build123d first3 validation version 0.1.0; unvalidated 1.16%
  766. 766 CADGenBench submission zky_pi-agent-qwen3-8-101-103_20260903-115005: Pi Agent Qwen3.8-101+103 version 0.1.0; unvalidated 1.16%
  767. 767 CADGenBench submission arisa_gpt-5-6-sol-visual-check-oneshot-101-ste_20260915-080620: GPT-5.6-sol-visual-check-oneshot-101-step-128-r1 version 0.1.0; unvalidated 1.15%
  768. 768 CADGenBench submission independent-cad-workflow_blind-fixture-215-end-disc-thickness-1-t_20260815-095040: Blind fixture 215 end disc thickness 1 to 2 run001 version 0.1.0; unvalidated 1.14%
  769. 769 CADGenBench submission w1ne_kernelcad-probe-tiny-20261019_20261019-150640: kernelcad-probe-tiny-20261019 version 0.1.0; unvalidated 1.13%
  770. 770 CADGenBench submission reify_reify-deepseek-low-naked-215-export-fix-_20261022-091801: reify-deepseek-low-naked-215-export-fix-01 version 0.1.0; unvalidated 1.13%
  771. 771 CADGenBench submission jake-fitzgerald_codex-cad-skill-first3-validation_20260609-105454: Codex cad skill first3 validation version 0.1.0; unvalidated 1.12%
  772. 772 CADGenBench submission wolf_cadgenresearch-102-103_20260907-105849: CADgenResearch-102+103 version 0.1.0; unvalidated 1.09%
  773. 773 CADGenBench submission cad-experiment_two-task-cad-experiment-120-241_20260916-005258: Two-task CAD experiment (120, 241) version 0.1.0; unvalidated 1.09%
  774. 774 CADGenBench submission draw2cad_draw2cad-drawing-derived-101-2026-09-13_20260912-155517: draw2cad drawing-derived 101 2026-09-13 version 0.1.0; unvalidated 1.07%
  775. 775 CADGenBench submission yitong42_codex-gpt-5-6-sol-high-3-sample-diagnost_20260808-084612: Codex + gpt-5.6-sol high (3-sample diagnostic) version 0.1.0; unvalidated 1.06%
  776. 776 CADGenBench submission independent-cad-workflow_blind-fixture-214-edit-run001_20260813-125249: Blind fixture 214 edit run001 version 0.1.0; unvalidated 1.06%
  777. 777 CADGenBench submission cad-mcp-research_canonical-frame-v0-3-17-task105-diagnost_20260823-234206: canonical-frame v0.3.17 task105 diagnostic cell-e24ead3d40780c161662 version 0.1.0; unvalidated 1.06%
  778. 778 CADGenBench submission independent-cad-workflow_blind-fixture-224-edit-run001_20260813-133148: Blind fixture 224 edit run001 version 0.1.0; unvalidated 1.05%
  779. 779 CADGenBench submission anonymous_anon-gen-1789073510-472d47_20260910-205208: anon-gen-1789073510-472d47 version 0.1.0; unvalidated 1.05%
  780. 780 CADGenBench submission xyz_gpt-5-6-sol-incremental-v1-generic-stage_20260918-062517: GPT-5.6-sol-incremental-v1-generic-stages-v2-high-step-101-102-r1 version 0.1.0; unvalidated 1.05%
  781. 781 CADGenBench submission lindacyffan_pi-agent-qwen3-8-steps-115-128_20260907-045831: Pi Agent - Qwen3.8-steps-115+128 version 0.1.0; unvalidated 1.02%
  782. 782 CADGenBench submission mix_20260920-gpt-5-6-sol-mix-step-101-xhigh-_20260920-142607: 20260920-GPT-5.6-sol-mix-step-101-xhigh-102-high-r1 version 0.1.0; unvalidated 1.00%
  783. 783 CADGenBench submission mliu_chamfer-cad-harness-0-1-2-dev2_20260707-071439: chamfer-cad-harness-0.1.2.dev2 version 0.1.0; unvalidated 0.99%
  784. 784 CADGenBench submission anonymous_anon-gen-1789073510-1ff981_20260910-210109: anon-gen-1789073510-1ff981 version 0.1.0; unvalidated 0.98%
  785. 785 CADGenBench submission o-uz_o-uz-chatgpt-build123d-task-109-pilot-v0_20260817-123006: OĞUZ ChatGPT-build123d Task 109 Pilot v0.1 version 0.1.0; unvalidated 0.96%
  786. 786 CADGenBench submission yitong42_codex-gpt-6-astra-ultra-self-reconstruct_20260906-161753: Codex GPT-6 Astra Ultra self-reconstructed SVG-CAD (case 102) version 0.1.0; unvalidated 0.94%
  787. 787 CADGenBench submission lindacyffan_pi-agent-qwen3-8-128_20260907-031448: Pi Agent - Qwen3.8-128 version 0.1.0; unvalidated 0.93%
  788. 788 CADGenBench submission xyz_gpt-5-6-sol-oneshot-visual-check-high-10_20260918-062536: GPT-5.6-sol-oneshot-visual-check-high-101-102-r1 version 0.1.0; unvalidated 0.92%
  789. 789 CADGenBench submission lindacyffan_cadresearch-128_20260907-091307: CADResearch-128 version 0.1.0; unvalidated 0.91%
  790. 790 CADGenBench submission high_20260920-gpt-5-6-sol-incremental-v1-gene_20260920-123924: 20260920-GPT-5.6-sol-incremental-v1-generic-stages-v2-high-step-101-r2 version 0.1.0; unvalidated 0.91%
  791. 791 CADGenBench submission mliu_chamfer-cad-harness-0-1-2-dev2_20260707-085910: chamfer-cad-harness-0.1.2.dev2 version 0.1.0; unvalidated 0.90%
  792. 792 CADGenBench submission lindacyffan_cadresearch-steps-128_20260907-091409: CADResearch-steps-128 version 0.1.0; unvalidated 0.90%
  793. 793 CADGenBench submission anonymous_anon-edit-1788072384-a74e_20260830-064625: anon-edit-1788072384-a74e version 0.1.0; unvalidated 0.89%
  794. 794 CADGenBench submission zky_pi-agent-glm-5-3-flash-fixtures-101-103_20260902-064301: Pi Agent GLM-5.3-Flash fixtures 101-103 version 0.1.0; unvalidated 0.89%
  795. 795 CADGenBench submission xyz_20260920-gpt-5-6-sol-oneshot-visual-chec_20260920-073517: 20260920-GPT-5.6-sol-oneshot-visual-check-xhigh-102-143-r1 version 0.1.0; unvalidated 0.89%
  796. 796 CADGenBench submission xyz_20260920-gpt-5-6-sol-incremental-v1-gene_20260920-073552: 20260920-GPT-5.6-sol-incremental-v1-generic-stages-v2-xhigh-step-102-143-r1 version 0.1.0; unvalidated 0.86%
  797. 797 CADGenBench submission lindacyffan_pi-agent-qwen3-8-steps-128_20260907-031554: Pi Agent - Qwen3.8-steps-128 version 0.1.0; unvalidated 0.85%
  798. 798 CADGenBench submission anonymous_anon-gen-1789083011-300e52_20260911-005533: anon-gen-1789083011-300e52 version 0.1.0; unvalidated 0.85%
  799. 799 CADGenBench submission origogk_origogk-diagnostic-149-voxel-1mm_20260925-153940: OrigoGK diagnostic 149 voxel-1mm version 0.1.0; unvalidated 0.85%
  800. 800 CADGenBench submission independent-cad-workflow_blind-fixture-211-top-surface-10-run001_20260815-091450: Blind fixture 211 top surface +10 run001 version 0.1.0; unvalidated 0.84%
  801. 801 CADGenBench submission cad-mcp-research_axis-grounded-review-v0-3-8-task105-diag_20260823-203421: axis-grounded-review v0.3.8 task105 diagnostic cell-27fc476f16350bcadf75 version 0.1.0; unvalidated 0.83%
  802. 802 CADGenBench submission local-user_t047-repair-b-103-20261027_20261027-120251: t047-repair-b-103-20261027 version 0.1.0; unvalidated 0.83%
  803. 803 CADGenBench submission cad-mcp-research_topology-grounded-v0-3-4-diagnostic-cell_20260823-162546: topology-grounded v0.3.4 diagnostic cell-7c368edcabea6bab12ae version 0.1.0; unvalidated 0.82%
  804. 804 CADGenBench submission cad-mcp-research_visual-source-review-v0-3-6-task105-diag_20260823-193859: visual-source-review v0.3.6 task105 diagnostic cell-20f0e795affaafcc30b0 version 0.1.0; unvalidated 0.79%
  805. 805 CADGenBench submission anonymous_anon-edit-1788156537-2756_20260831-060858: anon-edit-1788156537-2756 version 0.1.0; unvalidated 0.78%
  806. 806 CADGenBench submission mix_20260920-gpt-5-6-sol-mix-oneshot-101-xhi_20260920-142541: 20260920-GPT-5.6-sol-mix-oneshot-101-xhigh-102-high-r1 version 0.1.0; unvalidated 0.78%
  807. 807 CADGenBench submission cad-mcp-research_stepped-port-semantics-v0-3-16-task105-d_20260823-224210: stepped-port-semantics v0.3.16 task105 diagnostic cell-a2c78183b51bec3444bd version 0.1.0; unvalidated 0.77%
  808. 808 CADGenBench submission zky_pi-agent-glm-5-3-flash-fixtures-101-102_20260901-155807: Pi Agent GLM-5.3-Flash fixtures 101-102 version 0.1.0; unvalidated 0.77%
  809. 809 CADGenBench submission cadse_probe-flipx-part-150-of-the-lean-repeat-_20261112-082959: probe flipx: part 150 of the lean repeat turned 180 deg about X, pose test, 1 fixture version 0.1.0; unvalidated 0.76%
  810. 810 CADGenBench submission independent-cad-workflow_blind-fixture-132-run001_20260812-155030: Blind fixture 132 run001 version 0.1.0; unvalidated 0.75%
  811. 811 CADGenBench submission cad-mcp-research_visual-source-review-v0-3-6-task105-diag_20260823-194437: visual-source-review v0.3.6 task105 diagnostic cell-397350b933b119cdb308 version 0.1.0; unvalidated 0.75%
  812. 812 CADGenBench submission cad-mcp-research_topology-grounded-v0-3-4-diagnostic-cell_20260823-161915: topology-grounded v0.3.4 diagnostic cell-241c6c8e2c57645cbc93 version 0.1.0; unvalidated 0.74%
  813. 813 CADGenBench submission local-user_t047-repair-p2-103-20261027_20261027-120454: t047-repair-p2-103-20261027 version 0.1.0; unvalidated 0.74%
  814. 814 CADGenBench submission cadse_probe-rotz-part-150-of-the-lean-repeat-t_20261112-083034: probe rotz: part 150 of the lean repeat turned 180 deg about Z, pose test, 1 fixture version 0.1.0; unvalidated 0.74%
  815. 815 CADGenBench submission wolf_cadgenresearchs-103_20260908-023535: CADgenResearchs-103 version 0.1.0; unvalidated 0.73%
  816. 816 CADGenBench submission cad-mcp-research_constraint-verified-v0-3-3-diagnostic-ce_20260823-143430: constraint-verified v0.3.3 diagnostic cell-b638afa5499f71d46e2b version 0.1.0; unvalidated 0.72%
  817. 817 CADGenBench submission cad-mcp-research_constraint-verified-v0-3-3-diagnostic-ce_20260823-144049: constraint-verified v0.3.3 diagnostic cell-1950efc045c9ce03d939 version 0.1.0; unvalidated 0.72%
  818. 818 CADGenBench submission lindacyffan_pi-agent-qwen3-8-steps-102-143_20260907-020424: Pi Agent - Qwen3.8-steps- 102+143 version 0.1.0; unvalidated 0.72%
  819. 819 CADGenBench submission cad-mcp-research_axis-grounded-review-v0-3-8-task105-diag_20260823-202617: axis-grounded-review v0.3.8 task105 diagnostic cell-10fb08d05b9706e8922a version 0.1.0; unvalidated 0.71%
  820. 820 CADGenBench submission zky_pi-agent-glm-5-3-flash-fixtures-103-free_20260902-104810: Pi Agent GLM-5.3-Flash fixtures 103（free） version 0.1.0; unvalidated 0.71%
  821. 821 CADGenBench submission zky_pi-agent-glm-5-3-flash-fixtures-103-free_20260902-124125: Pi Agent GLM-5.3-Flash fixtures 103（free-3） version 0.1.0; unvalidated 0.71%
  822. 822 CADGenBench submission lindacyffan_pi-agent-qwen3-8-102-143_20260907-020249: Pi Agent - Qwen3.8- 102+143 version 0.1.0; unvalidated 0.71%
  823. 823 CADGenBench submission cadse_probe-d-part-150-of-the-hole-rules-run-w_20261112-084743: probe d: part 150 of the hole-rules run with the rear slope starting later, 1 fixture version 0.1.0; unvalidated 0.71%
  824. 824 CADGenBench submission cadse_probe-a-part-150-of-the-hole-rules-run-w_20261112-084610: probe a: part 150 of the hole-rules run with shorter floor slots, 1 fixture version 0.1.0; unvalidated 0.70%
  825. 825 CADGenBench submission cadse_probe-b-part-150-of-the-hole-rules-run-w_20261112-084704: probe b: part 150 of the hole-rules run with the 15 mm hole from the top face, 1 fixture version 0.1.0; unvalidated 0.70%
  826. 826 CADGenBench submission cad-mcp-research_inspection-first-diagnostic-cell-eefa0cc_20260824-015832: inspection-first diagnostic cell-eefa0cca2d7cf5523cdd version 0.1.0; unvalidated 0.68%
  827. 827 CADGenBench submission zky_pi-agent-qwen3-8-103_20260903-122207: Pi Agent Qwen3.8-103 version 0.1.0; unvalidated 0.68%
  828. 828 CADGenBench submission reify_reify-deepseek-v4-1-flash-medium-assiste_20261021-062037: Reify DeepSeek v4.1 Flash medium - assisted 101 201 pilot version 0.1.0; unvalidated 0.64%
  829. 829 CADGenBench submission cad-mcp-research_stepped-port-semantics-v0-3-16-task105-d_20260823-225025: stepped-port-semantics v0.3.16 task105 diagnostic cell-cef4882a7ec02ae5312c version 0.1.0; unvalidated 0.61%
  830. 830 CADGenBench submission zky_pi-agent-glm-5-3-flash-fixtures-103-1_20260902-103111: Pi Agent GLM-5.3-Flash fixtures 103（1） version 0.1.0; unvalidated 0.61%
  831. 831 CADGenBench submission abc_gpt-5-6-sol-stage-ablation-baseline-v1-h_20260916-130122: GPT-5.6-sol-stage-ablation-baseline-v1-high-101 version 0.1.0; unvalidated 0.61%
  832. 832 CADGenBench submission reify_reify-deepseek-low-asi-hard-edit-204-241_20261023-154259: reify-deepseek-low-asi-hard-edit-204-241-243-01 version 0.1.0; unvalidated 0.61%
  833. 833 CADGenBench submission reify_reify-deepseek-low-naked-204-01_20261024-055930: reify-deepseek-low-naked-204-01 version 0.1.0; unvalidated 0.61%
  834. 834 CADGenBench submission universe_20260920-gpt-5-6-sol-oneshot-visual-chec_20260920-083649: 20260920-GPT-5.6-sol-oneshot-visual-check-xhigh-101-r1 version 0.1.0; unvalidated 0.60%
  835. 835 CADGenBench submission reify_reify-sol-low-naked-asi-201-comparison_20261021-160613: reify-sol-low-naked-asi-201-comparison version 0.1.0; unvalidated 0.60%
  836. 836 CADGenBench submission wolf_cadgenresearchs103_20260908-023513: CADgenResearchs103 version 0.1.0; unvalidated 0.59%
  837. 837 CADGenBench submission niming_a-research_20261001-134447: a_research version 0.1.0; unvalidated 0.59%
  838. 838 CADGenBench submission abc_gpt-5-6-sol-stage-ablation-reread-v1-hig_20260916-130223: GPT-5.6-sol-stage-ablation-reread-v1-high-101 version 0.1.0; unvalidated 0.57%
  839. 839 CADGenBench submission pzfreo_gpt55-v0377-xhigh-gen3-dominant_20260710-062829: gpt55-v0377-xhigh-gen3-dominant version 0.1.0; unvalidated 0.55%
  840. 840 CADGenBench submission lehuili_gpt-5-6-visual-findings-no-dual-roi-case_20260822-211640: GPT-5.6 Visual Findings No Dual ROI (Case 103) version 0.1.0; unvalidated 0.54%
  841. 841 CADGenBench submission lehuili_gpt-5-6-sol-optional-reflect-code-ablati_20260830-111204: GPT-5.6 Sol Optional Reflect + Code Ablation (Case 103) version 0.1.0; unvalidated 0.54%
  842. 842 CADGenBench submission amy_gpt-5-6-sol-incremental-v1-high-step-101_20260916-092831: GPT-5.6-sol-incremental-v1-high-step-101 version 0.1.0; unvalidated 0.54%
  843. 843 CADGenBench submission charif_antigravity-build123d-agent_20260905-204201: Antigravity Build123d Agent version 0.1.0; unvalidated 0.53%
  844. 844 CADGenBench submission abc_gpt-5-6-sol-stage-ablation-focus-v1-high_20260916-130201: GPT-5.6-sol-stage-ablation-focus-v1-high-101 version 0.1.0; unvalidated 0.53%
  845. 845 CADGenBench submission zky_pi-agent-glm-5-3-flash-fixtures-103-free_20260903-061910: Pi Agent GLM-5.3-Flash fixtures 103（free-1） version 0.1.0; unvalidated 0.52%
  846. 846 CADGenBench submission local-user_t046-cgb101-0770-local-v1_20261026-072818: t046-cgb101-0770-local-v1 version 0.1.0; unvalidated 0.52%
  847. 847 CADGenBench submission pzfreo_gpt55-v0371-xhigh-tricky3-retry_20260707-122755: gpt55-v0371-xhigh-tricky3-retry version 0.1.0; unvalidated 0.51%
  848. 848 CADGenBench submission lehuili_gpt-5-6-optional-reflect-persistent-visu_20260822-204648: GPT-5.6 Optional Reflect + Persistent Visual Findings + 2D Completion (Case 103) version 0.1.0; unvalidated 0.51%
  849. 849 CADGenBench submission lehuili_gpt-5-6-sol-causal-repair-diverse-hypoth_20260822-170015: GPT-5.6 Sol Causal Repair Diverse Hypotheses (Case 103) version 0.1.0; unvalidated 0.51%
  850. 850 CADGenBench submission lindacyffan_pi-agent-qwen3-8-steps-115_20260907-064326: Pi Agent - Qwen3.8-steps-115 version 0.1.0; unvalidated 0.50%
  851. 851 CADGenBench submission anonymous_anon-edi-1789088523-2764d8_20260911-010231: anon-edi-1789088523-2764d8 version 0.1.0; unvalidated 0.50%
  852. 852 CADGenBench submission independent-cad-workflow_blind-fixture-247-edit-run001_20260813-120356: Blind fixture 247 edit run001 version 0.1.0; unvalidated 0.49%
  853. 853 CADGenBench submission nrocketmann_cad-agent-deep-build-probe-2-of-81-fixtu_20260831-231311: cad-agent Deep Build probe (2 of 81 fixtures) version 0.1.0; unvalidated 0.49%
  854. 854 CADGenBench submission pzfreo_build123d-mcp-0-3-85-dev0-opus-5-xhigh_20260904-183253: build123d-mcp-0.3.85.dev0-opus-5-xhigh version 0.1.0; unvalidated 0.49%
  855. 855 CADGenBench submission arisa_gpt-5-6-sol-step-wise-strategy-v1-increm_20260915-020357: GPT-5.6-sol-step-wise-strategy-v1-incremental-visual-check-r1-101 version 0.1.0; unvalidated 0.49%
  856. 856 CADGenBench submission xyz_gpt-5-6-sol-incremental-v1-high-pi-agent_20260917-122313: GPT-5.6-sol-incremental-v1-high-pi-agent-103-r1 version 0.1.0; unvalidated 0.49%
  857. 857 CADGenBench submission xyz_gpt-5-6-sol-incremental-v1-high-step-103_20260917-122339: GPT-5.6-sol-incremental-v1-high-step-103-r1 version 0.1.0; unvalidated 0.49%
  858. 858 CADGenBench submission anonymous_anon-edit-1788239926-61c9_20260901-051847: anon-edit-1788239926-61c9 version 0.1.0; unvalidated 0.47%
  859. 859 CADGenBench submission high_20260920-gpt-5-6-sol-oneshot-visual-chec_20260920-123853: 20260920-GPT-5.6-sol-oneshot-visual-check-high-101-r2 version 0.1.0; unvalidated 0.47%
  860. 860 CADGenBench submission charif_antigravity-build123d_20260903-141338: Antigravity Build123d version 0.1.0; unvalidated 0.45%
  861. 861 CADGenBench submission anonymous_anon-edi-1789073510-b03ffd_20260910-210642: anon-edi-1789073510-b03ffd version 0.1.0; unvalidated 0.45%
  862. 862 CADGenBench submission abc_gpt-5-6-sol-stage-ablation-visual-loop-v_20260916-130238: GPT-5.6-sol-stage-ablation-visual-loop-v1-high-101 version 0.1.0; unvalidated 0.45%
  863. 863 CADGenBench submission universe_20260920-gpt-5-6-sol-incremental-v1-gene_20260920-083614: 20260920-GPT-5.6-sol-incremental-v1-generic-stages-v2-xhigh-step-101-r1 version 0.1.0; unvalidated 0.45%
  864. 864 CADGenBench submission cadgenbench-2d-to-3d_dxf-to-fusion-0-6-6-2-track-b-subset-150_20261012-142153: dxf-to-fusion 0.6.6.2 Track B subset (150/129/120) version 0.1.0; unvalidated 0.45%
  865. 865 CADGenBench submission version5_101-no-step-1_20260909-072608: 101-no_step-1 version 0.1.0; unvalidated 0.44%
  866. 866 CADGenBench submission anonymous_anon-edit-1788135725-f790_20260831-002206: anon-edit-1788135725-f790 version 0.1.0; unvalidated 0.42%
  867. 867 CADGenBench submission anonymous_anon-gen-1788292278-d51a_20260901-195119: anon-gen-1788292278-d51a version 0.1.0; unvalidated 0.42%
  868. 868 CADGenBench submission version5_101-step-2_20260909-072653: 101-_step-2 version 0.1.0; unvalidated 0.42%
  869. 869 CADGenBench submission zky_pi-agent-glm-5-3-flash-fixtures-103_20260902-093620: Pi Agent GLM-5.3-Flash fixtures 103 version 0.1.0; unvalidated 0.41%
  870. 870 CADGenBench submission wolf_101_20260908-050030: 101 version 0.1.0; unvalidated 0.41%
  871. 871 CADGenBench submission zky_pi-agent-glm-5-3-flash-fixture-101_20260901-152620: Pi Agent GLM-5.3-Flash fixture 101 version 0.1.0; unvalidated 0.40%
  872. 872 CADGenBench submission zky_pi-agent-qwen3-8-101_20260906-081914: Pi Agent - Qwen3.8-101 version 0.1.0; unvalidated 0.39%
  873. 873 CADGenBench submission zky_pi-agent-steps-qwen3-8-101_20260906-081610: Pi Agent + steps - Qwen3.8-101 version 0.1.0; unvalidated 0.39%
  874. 874 CADGenBench submission wolf_101-step_20260908-055041: 101+step version 0.1.0; unvalidated 0.39%
  875. 875 CADGenBench submission amy_gpt-5-6-sol-incremental-v1-high-pi-agent_20260916-092808: GPT-5.6-sol-incremental-v1-high-pi-agent-101 version 0.1.0; unvalidated 0.39%
  876. 876 CADGenBench submission wolf_101-step_20260908-050131: 101-step version 0.1.0; unvalidated 0.38%
  877. 877 CADGenBench submission version5_101-no-step-2_20260909-072631: 101-no_step-2 version 0.1.0; unvalidated 0.38%
  878. 878 CADGenBench submission version5_101-step-1_20260909-072729: 101-_step-1 version 0.1.0; unvalidated 0.38%
  879. 879 CADGenBench submission independent-cad-workflow_blind-fixture-147-run001_20260812-143651: Blind fixture 147 run001 version 0.1.0; unvalidated 0.37%
  880. 880 CADGenBench submission cad-mcp-research_inspection-first-diagnostic-cell-1dd2bf1_20260824-025803: inspection-first diagnostic cell-1dd2bf12c6601f0c9768 version 0.1.0; unvalidated 0.37%
  881. 881 CADGenBench submission anonymous_cadgenbench-111-148-test_20260905-130419: CADGenBench 111+148 test version 0.1.0; unvalidated 0.37%
  882. 882 CADGenBench submission zky_pi-agent-qwen3-8-101_20260906-084559: Pi Agent - Qwen3.8- 101 version 0.1.0; unvalidated 0.37%
  883. 883 CADGenBench submission zky_pi-agent-steps-qwen3-8-101_20260906-081537: Pi Agent + steps - Qwen3.8-101 version 0.1.0; unvalidated 0.37%
  884. 884 CADGenBench submission abc_gpt-5-6-sol-incremental-v1-high-step-101_20260917-050510: GPT-5.6-sol-incremental-v1-high-step-101-r2 version 0.1.0; unvalidated 0.37%
  885. 885 CADGenBench submission independent-cad-workflow_blind-fixture-105-generation-run001_20260820-133942: Blind fixture 105 generation run001 version 0.1.0; unvalidated 0.36%
  886. 886 CADGenBench submission cad-mcp-research_inspection-first-diagnostic-cell-87cfd25_20260824-025121: inspection-first diagnostic cell-87cfd25994da8be2ca7b version 0.1.0; unvalidated 0.35%
  887. 887 CADGenBench submission anonymous_anon-gen-1788239802-e5be_20260901-051643: anon-gen-1788239802-e5be version 0.1.0; unvalidated 0.35%
  888. 888 CADGenBench submission anonymous_anon-gen-1788315559-f1d3_20260902-021920: anon-gen-1788315559-f1d3 version 0.1.0; unvalidated 0.35%
  889. 889 CADGenBench submission anonymous_anon-gen-1788372413-975c_20260902-180654: anon-gen-1788372413-975c version 0.1.0; unvalidated 0.35%
  890. 890 CADGenBench submission anonymous_anon-gen-1788372526-ef78_20260902-180848: anon-gen-1788372526-ef78 version 0.1.0; unvalidated 0.35%
  891. 891 CADGenBench submission cad-mcp-research_canonical-frame-v0-3-17-task105-diagnost_20260823-231225: canonical-frame v0.3.17 task105 diagnostic cell-129aea4b2a0da94083a2 version 0.1.0; unvalidated 0.34%
  892. 892 CADGenBench submission abc_gpt-5-6-sol-incremental-v1-high-pi-agent_20260917-055601: GPT-5.6-sol-incremental-v1-high-pi-agent-101-r2 version 0.1.0; unvalidated 0.34%
  893. 893 CADGenBench submission cad-mcp-research_inspection-first-diagnostic-cell-522bc3d_20260824-035018: inspection-first diagnostic cell-522bc3d7f43296e096fa version 0.1.0; unvalidated 0.33%
  894. 894 CADGenBench submission cad-mcp-research_baseline-protected-v0-7-9-diagnostic-cel_20260824-151012: baseline-protected v0.7.9 diagnostic cell-de8b1f53d7d7f7d8bd2d version 0.1.0; unvalidated 0.32%
  895. 895 CADGenBench submission reify_reify-deepseek-v4-1-flash-low-asi-201-pi_20261021-131436: reify-deepseek-v4-1-flash-low-asi-201-pilot version 0.1.0; unvalidated 0.32%
  896. 896 CADGenBench submission anonymous_anon-r1_20260914-093726: anon-r1 version 0.1.0; unvalidated 0.31%
  897. 897 CADGenBench submission independent-cad-workflow_blind-fixture-135-run001_20260812-110543: Blind fixture 135 run001 version 0.1.0; unvalidated 0.30%
  898. 898 CADGenBench submission cad-mcp-research_baseline-protected-v0-7-9-diagnostic-cel_20260824-152358: baseline-protected v0.7.9 diagnostic cell-3b76b44215889537685b version 0.1.0; unvalidated 0.30%
  899. 899 CADGenBench submission cad-mcp-research_inspection-first-diagnostic-cell-390e124_20260824-040229: inspection-first diagnostic cell-390e1241465919b85df2 version 0.1.0; unvalidated 0.30%
  900. 900 CADGenBench submission lindacyffan_pi-agent-qwen3-8-115_20260907-064412: Pi Agent - Qwen3.8-115 version 0.1.0; unvalidated 0.30%
  901. 901 CADGenBench submission cad-mcp-research_visual-source-review-v0-3-6-task108-diag_20260823-192923: visual-source-review v0.3.6 task108 diagnostic cell-e4ee681e0ee6afde0895 version 0.1.0; unvalidated 0.29%
  902. 902 CADGenBench submission cad-mcp-research_canonical-frame-v0-3-17-task112-diagnost_20260824-002039: canonical-frame v0.3.17 task112 diagnostic cell-e83020eae58980dc6d1b version 0.1.0; unvalidated 0.28%
  903. 903 CADGenBench submission cad-mcp-research_inspection-first-diagnostic-cell-309f7a3_20260824-030425: inspection-first diagnostic cell-309f7a37fc4fda81d9c4 version 0.1.0; unvalidated 0.28%
  904. 904 CADGenBench submission wolf_101-pi-agent_20260908-054958: 101+pi-agent version 0.1.0; unvalidated 0.27%
  905. 905 CADGenBench submission cad-mcp-research_inspection-first-diagnostic-cell-9c5dd79_20260824-031058: inspection-first diagnostic cell-9c5dd797047d13334d3f version 0.1.0; unvalidated 0.26%
  906. 906 CADGenBench submission cad-mcp-research_topology-grounded-v0-3-4-task108-diagnos_20260823-170624: topology-grounded v0.3.4 task108 diagnostic cell-110a7bc4f6be74849f52 version 0.1.0; unvalidated 0.24%
  907. 907 CADGenBench submission cad-mcp-research_canonical-frame-v0-3-17-task112-diagnost_20260824-001136: canonical-frame v0.3.17 task112 diagnostic cell-e7ff97b17c58e72daddb version 0.1.0; unvalidated 0.24%
  908. 908 CADGenBench submission cad-mcp-research_source-reinspection-v0-3-5-task108-diagn_20260823-180206: source-reinspection v0.3.5 task108 diagnostic cell-a1bdca8fc9a8516db2df version 0.1.0; unvalidated 0.23%
  909. 909 CADGenBench submission cad-mcp-research_visual-source-review-v0-3-6-task108-diag_20260823-185916: visual-source-review v0.3.6 task108 diagnostic cell-7a3944ae3ceafbce8064 version 0.1.0; unvalidated 0.23%
  910. 910 CADGenBench submission cad-mcp-research_inspection-first-diagnostic-cell-72c16d1_20260824-031720: inspection-first diagnostic cell-72c16d112fb989a8fe48 version 0.1.0; unvalidated 0.23%
  911. 911 CADGenBench submission michaelr27_pipeline-smoke-test-box_20260627-135608: Pipeline smoke test (box) version 0.1.0; unvalidated 0.19%
  912. 912 CADGenBench submission cad-mcp-research_canonical-frame-v0-3-17-task108-diagnost_20260823-235239: canonical-frame v0.3.17 task108 diagnostic cell-538fe6617610d443d89f version 0.1.0; unvalidated 0.18%
  913. 913 CADGenBench submission cad-mcp-research_source-reinspection-v0-3-5-task108-diagn_20260823-175319: source-reinspection v0.3.5 task108 diagnostic cell-847743c3b96ae944b081 version 0.1.0; unvalidated 0.16%
  914. 914 CADGenBench submission draw2cad_draw2cad-wiring-smoke-2026-09-06_20260906-141211: draw2cad wiring smoke 2026-09-06 version 0.1.0; unvalidated 0.15%
  915. 915 CADGenBench submission cad-mcp-research_topology-grounded-v0-3-4-task108-diagnos_20260823-170052: topology-grounded v0.3.4 task108 diagnostic cell-98e3f7952ceed293cf36 version 0.1.0; unvalidated 0.14%
  916. 916 CADGenBench submission local-test_fake-mesh-upload-smoke-test_20260612-063710: Fake mesh upload smoke test version 0.1.0; unvalidated 0.11%
  917. 917 CADGenBench submission reify_reify-sol-low-naked-201-comparison_20261021-160213: reify-sol-low-naked-201-comparison version 0.1.0; unvalidated 0.08%
  918. 918 CADGenBench submission cad-mcp-research_canonical-frame-v0-3-17-task108-diagnost_20260823-235844: canonical-frame v0.3.17 task108 diagnostic cell-84cac741adb0ef74a571 version 0.1.0; unvalidated 0%

Source: Official CADGenBench leaderboard

Sources: Official CADGenBench leaderboard and labs’ model cards

#EntryScoreSettingDateSource
1 CADGenBench submission godela_godela-modernized-agentic_20261109-183706: Godela - Modernized Agentic 85.1% version 0.1.0; validated, Godela Nov 2026 Official leaderboard
2 CADGenBench submission standard-manufacturing-co_smc-harness-fable-5-2-max_20261111-165655: SMC Harness + Fable 5.2 Max 85.1% version 0.1.0; unvalidated, Standard Manufacturing Co Nov 2026 Official leaderboard
3 CADGenBench submission deeprd_deeprd-v2_20261011-092629: deeprd-v2 84.8% version 0.1.0; unvalidated, deeprd Oct 2026 Official leaderboard
4 CADGenBench submission rexl2018_vextcad-vxl-agent-r1_20261107-142023: VextCAD VXL agent (r1) 84.4% version 0.1.0; unvalidated, rexl2018 Nov 2026 Official leaderboard
5 CADGenBench submission deeprd_deeprd_20261011-060231: deeprd 83.7% version 0.1.0; unvalidated, deeprd Oct 2026 Official leaderboard
6 CADGenBench submission muhammed-ikbal-arikan_arikan-siemens-nx-mcp-claude-opus-5-5_20261006-044721: Arikan_Siemens_NX_MCP + Claude Opus 5.5 83.5% version 0.1.0; unvalidated, Muhammed Ikbal Arikan Oct 2026 Official leaderboard
7 CADGenBench submission nik6_cad-ai-v11-4_20261014-200204: CAD AI V11.4 83.2% version 0.1.0; unvalidated, Nik6 Oct 2026 Official leaderboard
8 CADGenBench submission pzfreo_build123d-mcp-0-3-85-mcp-server-claude-o_20260924-101549: build123d-mcp 0.3.85 MCP server + Claude Opus 5.5 (max effort) r2 83% version 0.1.0; validated, pzfreo Sep 2026 Official leaderboard
9 CADGenBench submission nik6_cad-ai-v11-3_20261014-184426: CAD AI V11.3 82.9% version 0.1.0; unvalidated, Nik6 Oct 2026 Official leaderboard
10 CADGenBench submission nik6_cad-ai-v11-all81-four-editing-reruns-opu_20261014-151205: CAD AI V11 all81 four editing reruns (Opus5.5) 82.9% version 0.1.0; unvalidated, Nik6 Oct 2026 Official leaderboard
11 CADGenBench submission nik6_cad-ai-v11-all81-fresh149-rerun-opus5-5_20261014-164341: CAD AI V11 all81 fresh149 rerun (Opus5.5) 82.9% version 0.1.0; unvalidated, Nik6 Oct 2026 Official leaderboard
12 CADGenBench submission nik6_cad-ai-v11-2_20261014-180126: CAD AI V11.2 82.9% version 0.1.0; unvalidated, Nik6 Oct 2026 Official leaderboard
13 CADGenBench submission pzfreo_build123d-mcp-0-3-90-mcp-server-claude-o_20260926-100215: build123d-mcp 0.3.90 MCP server + Claude Opus 5.5 (max effort) R2.3 82.7% version 0.1.0; unvalidated, pzfreo Sep 2026 Official leaderboard
14 CADGenBench submission symge_symge-claude-opus-5-5-agentic-hybrid_20260926-113258: Symge - Claude Opus 5.5: agentic hybrid 82.6% version 0.1.0; unvalidated, Symge Sep 2026 Official leaderboard
15 CADGenBench submission mechanical-reasoning_mechanical-reasoning-astra-xhigh_20261016-220931: Mechanical Reasoning — Astra xhigh 82.4% version 0.1.0; unvalidated, Mechanical Reasoning Oct 2026 Official leaderboard
16 CADGenBench submission pzfreo_build123d-mcp-0-3-86-mcp-server-claude-o_20260925-194429: build123d-mcp 0.3.86 MCP server + Claude Opus 5.5 (max effort) R2.2 82.4% version 0.1.0; unvalidated, pzfreo Sep 2026 Official leaderboard
17 CADGenBench submission mechanical-reasoning_mechanical-reasoning-astra-xhigh_20261017-024229: Mechanical Reasoning — Astra xhigh 82.2% version 0.1.0; unvalidated, Mechanical Reasoning Oct 2026 Official leaderboard
18 CADGenBench submission nik6_cad-ai-v11-all81-four-checkpoint-repairs_20261014-021956: CAD AI V11 all81 four checkpoint repairs (Opus 5.5) 82.2% version 0.1.0; unvalidated, Nik6 Oct 2026 Official leaderboard
19 CADGenBench submission atomic_atomic-cad-v3_20261102-200731: Atomic CAD v3 82% version 0.1.0; unvalidated, Atomic Nov 2026 Official leaderboard
20 CADGenBench submission pzfreo_build123d-mcp-0-3-90-claude-sonnet-5-5-m_20260929-151832: build123d MCP 0.3.90 + Claude Sonnet 5.5 (Max) 81.8% version 0.1.0; unvalidated, pzfreo Sep 2026 Official leaderboard
21 CADGenBench submission pzfreo_build123d-mcp-0-3-85-mcp-server-claude-o_20260924-093300: build123d-mcp 0.3.85 MCP server + Claude Opus 5.5 (max effort) 81.8% version 0.1.0; unvalidated, pzfreo Sep 2026 Official leaderboard
22 CADGenBench submission godela_godela_20260915-045120: Godela 81.1% version 0.1.0; validated, Godela Sep 2026 Official leaderboard
23 CADGenBench submission nik6_cad-ai-v11-all-81-complete-opus-5-5_20261013-023932: CAD AI V11 all 81 complete (Opus 5.5) 80.7% version 0.1.0; unvalidated, Nik6 Oct 2026 Official leaderboard
24 CADGenBench submission xueqinglin_gpt-6-astra-claude-code-20260917-104819_20260917-025938: gpt-6-astra_claude-code_20260917-104819 80.6% version 0.1.0; unvalidated, xueqinglin Sep 2026 Official leaderboard
25 CADGenBench submission pzfreo_build123d-mcp-0-3-84-mcp-server-claude-o_20260923-092859: build123d-mcp 0.3.84 MCP server + Claude Opus 5.5 (xhigh effort) 80.5% version 0.1.0; unvalidated, pzfreo Sep 2026 Official leaderboard
26 CADGenBench submission cadse_generation-v2-editing-brief-v2_20261112-175916: generation v2 + editing brief v2 79.7% version 0.1.0; unvalidated, CADSE Nov 2026 Official leaderboard
27 CADGenBench submission anonymous_anon-all-1788919650-351ecb_20260909-020747: anon-all-1788919650-351ecb 79.2% version 0.1.0; unvalidated, anonymous Sep 2026 Official leaderboard
28 CADGenBench submission cadse_v5-edits-full-run-v2-plus-31-built-edits_20261112-155101: v5 edits: full run v2 plus 31 built edits 78.1% version 0.1.0; unvalidated, CADSE Nov 2026 Official leaderboard
29 CADGenBench submission nik6_cad-ai-v11-full-benchmark-opus-5-5_20261011-213229: CAD AI V11 full benchmark (Opus 5.5) 76.9% version 0.1.0; unvalidated, Nik6 Oct 2026 Official leaderboard
30 CADGenBench submission atomic_atomic-cad-v2_20261022-043132: Atomic CAD v2 76.8% version 0.1.0; unvalidated, Atomic Oct 2026 Official leaderboard
31 CADGenBench submission atomic_atomic-cad-v2_20261022-072149: Atomic CAD v2 76.8% version 0.1.0; unvalidated, Atomic Oct 2026 Official leaderboard
32 CADGenBench submission zone404mars_zone-404-mars-freecad-harness-claude-opu_20261112-145855: Zone 404 Mars Freecad harness + Claude Opus 5.5 xhigh 76.6% version 0.1.0; unvalidated, Zone404Mars Nov 2026 Official leaderboard
33 CADGenBench submission nik6_nik6-harness-v9-claude-opus-5-5-high-eff_20261001-233943: nik6-harness-v9 + Claude Opus 5.5 (high effort) 76.2% version 0.1.0; unvalidated, Nik6 Oct 2026 Official leaderboard
34 CADGenBench submission tracycui_gpt-6-astra-high-hf-baseline-with-build1_20261023-031459: GPT-6 Astra high HF baseline with build123d 75.5% version 0.1.0; unvalidated, tracycui Oct 2026 Official leaderboard
35 CADGenBench submission pzfreo_claude-opus-5-5-xhigh-effort-official-ba_20260923-174740: Claude Opus 5.5 (xhigh effort), official baseline prompt 75.2% version 0.1.0; unvalidated, pzfreo Sep 2026 Official leaderboard
36 CADGenBench submission eren_symge-claude-opus-5-5_20260926-072929: Symge - Claude Opus 5.5 75.2% version 0.1.0; unvalidated, Eren Sep 2026 Official leaderboard
37 CADGenBench submission atomic_atomic-cad-v1_20261018-043044: Atomic CAD v1 74.7% version 0.1.0; unvalidated, Atomic Oct 2026 Official leaderboard
38 CADGenBench submission rexl2018_vextor-vxl-agent-r6_20261106-141850: Vextor VXL agent (r6) 73.1% version 0.1.0; unvalidated, rexl2018 Nov 2026 Official leaderboard
39 CADGenBench submission faber-ai_faber-ai-gpt6_20260906-132046: Faber AI - gpt6 71.6% version 0.1.0; unvalidated, Faber AI Sep 2026 Official leaderboard
40 CADGenBench submission pzfreo_build123d-mcp-0-3-85-dev0-with-gpt-6-ast_20260905-073202: build123d-mcp 0.3.85.dev0 with GPT-6 Astra (High) 71.5% version 0.1.0; unvalidated, pzfreo Sep 2026 Official leaderboard
41 CADGenBench submission wormo_build123d-mcp-0-3-85-dev0-gpt-6-astra-xh_20261030-034033: build123d-mcp-0.3.85.dev0-gpt-6-astra-xhigh-supplement-202-240-20261030 71.3% version 0.1.0; unvalidated, wormo Oct 2026 Official leaderboard
42 CADGenBench submission thomwolf_gpt-6-astra-high-cadgenbench-baseline-mi_20260909-144301: GPT-6 Astra (high) + CADGenBench baseline - missing retry 5 71.1% version 0.1.0; unvalidated, thomwolf Sep 2026 Official leaderboard
43 CADGenBench submission rexl2018_vextor-vxl-agent-r5_20261105-143509: Vextor VXL agent (r5) 70.9% version 0.1.0; unvalidated, rexl2018 Nov 2026 Official leaderboard
44 CADGenBench submission modelcorp_baseline-astra-codex-low-v1_20260905-013922: baseline-astra-codex-low-v1 70.5% version 0.1.0; unvalidated, modelcorp Sep 2026 Official leaderboard
45 CADGenBench submission wormo_build123d-mcp-0-3-85-dev0-gpt-6-astra-xh_20261030-013513: build123d-mcp-0.3.85.dev0-gpt-6-astra-xhigh-fresh-20261029t074303z 70.1% version 0.1.0; unvalidated, wormo Oct 2026 Official leaderboard
46 CADGenBench submission arche-industries_smith_20260828-220305: Smith 69.3% version 0.1.0; unvalidated, Arche Industries Aug 2026 Official leaderboard
47 CADGenBench submission pzfreo_build123d-mcp-0-3-85-dev0-opus-5-xhigh-r_20260905-125604: build123d MCP 0.3.85.dev0 — Opus 5 xhigh — recognition-guided editing 69% version 0.1.0; unvalidated, pzfreo Sep 2026 Official leaderboard
48 CADGenBench submission rexl2018_vextor-vxl-agent-r4_20261105-013443: Vextor VXL agent (r4) 68.8% version 0.1.0; unvalidated, rexl2018 Nov 2026 Official leaderboard
49 CADGenBench submission pzfreo_pzfreo-opus5-xhigh-mcp-drawing-evidence-_20260814-072949: pzfreo-opus5-xhigh-mcp-drawing-evidence-gen49-edit32 67.7% version 0.1.0; unvalidated, pzfreo Aug 2026 Official leaderboard
50 CADGenBench submission andrii-pytel_daedalus-reader-agent-opus-high_20261023-074129: Daedalus - reader agent (opus, high) 66.8% version 0.1.0; unvalidated, Andrii Pytel Oct 2026 Official leaderboard
51 CADGenBench submission cadse_v4-edits-full-run-v2-plus-9-built-edits-_20261112-145656: v4 edits: full run v2 plus 9 built edits and 18 unchanged editing inputs 66.7% version 0.1.0; unvalidated, CADSE Nov 2026 Official leaderboard
52 CADGenBench submission mecado_astra-high-mecado-baseline-with-build123_20260921-202238: Astra high Mecado Baseline with Build123d 66.2% version 0.1.0; unvalidated, Mecado Sep 2026 Official leaderboard
53 CADGenBench submission nik6_nik6-harness-c-v3_20260819-020220: nik6-harness-c-v3 65.8% version 0.1.0; unvalidated, Nik6 Aug 2026 Official leaderboard
54 CADGenBench submission webmesh_webmesh-v4_20261105-043522: WebMesh v4 65.2% version 0.1.0; unvalidated, WebMesh Nov 2026 Official leaderboard
55 CADGenBench submission nik6_nik6-harness-c-v2_20260818-031411: nik6-harness-c-v2 64.3% version 0.1.0; unvalidated, Nik6 Aug 2026 Official leaderboard
56 CADGenBench submission nataliya-shakhovska_daedalus-a4h-opus55-medium-r2_20261112-150429: daedalus-a4h-opus55-medium-r2 64.2% version 0.1.0; unvalidated, Nataliya Shakhovska Nov 2026 Official leaderboard
57 CADGenBench submission pzfreo_build123d-mcp-v0381-claude-opus-5-xhigh-_20260807-101147: build123d-mcp-v0381-claude-opus-5-xhigh-full-r6 63.9% version 0.1.0; validated, pzfreo Aug 2026 Official leaderboard
58 CADGenBench submission modelcorp_baseline-astra-codex-low-v0_20260904-225835: baseline-astra-codex-low-v0 63.7% version 0.1.0; unvalidated, modelcorp Sep 2026 Official leaderboard
59 CADGenBench submission saysolid-adapted-hub-llc_saysolid-gpt-6-1-sol-exact-dataset-nativ_20261025-071859: SaySolid gpt-6.1-sol exact-dataset-native-inputs visual-critic worker 682232c8535e 63.6% version 0.1.0; unvalidated, SaySolid / Adapted Hub LLC Oct 2026 Official leaderboard
60 CADGenBench submission saysolid-adapted-hub-llc_saysolid-gpt-6-1-sol-exact-dataset-nativ_20261025-145423: SaySolid gpt-6.1-sol exact-dataset-native-inputs visual-critic worker 682232c8535e 63.6% version 0.1.0; unvalidated, SaySolid / Adapted Hub LLC Oct 2026 Official leaderboard
61 CADGenBench submission nataliya-shakhovska_daedalus-a4h-opus55-medium-r1_20261112-150227: daedalus-a4h-opus55-medium-r1 63% version 0.1.0; unvalidated, Nataliya Shakhovska Nov 2026 Official leaderboard
62 CADGenBench submission nataliya-shakhovska_daedalus-a4h-opus55-medium-r3_20261112-150542: daedalus-a4h-opus55-medium-r3 63% version 0.1.0; unvalidated, Nataliya Shakhovska Nov 2026 Official leaderboard
63 CADGenBench submission mecado_astra-xhigh-mecado-baseline-with-build12_20260921-201510: Astra xhigh Mecado Baseline with Build123d 63% version 0.1.0; unvalidated, Mecado Sep 2026 Official leaderboard
64 CADGenBench submission andrii-pytel_daedalus-phased-pipeline-opus-medium_20261007-144742: Daedalus - phased pipeline (opus, medium) 62.9% version 0.1.0; unvalidated, Andrii Pytel Oct 2026 Official leaderboard
65 CADGenBench submission rexl2018_vextor-vxl-agent-engine-0030ca21-r3_20261103-142422: Vextor VXL agent (engine 0030ca21, r3) 62.7% version 0.1.0; unvalidated, rexl2018 Nov 2026 Official leaderboard
66 CADGenBench submission pzfreo_opus5-xhigh-official-baseline-prompt-nom_20260811-034944: opus5-xhigh-official-baseline-prompt-nomcp-complete-r1 62.7% version 0.1.0; unvalidated, pzfreo Aug 2026 Official leaderboard
67 CADGenBench submission andrii-pytel_daedalus-phased-pipeline-opus-high_20261023-105235: Daedalus - phased pipeline (opus, high) 62.6% version 0.1.0; unvalidated, Andrii Pytel Oct 2026 Official leaderboard
68 CADGenBench submission andrii-pytel_daedalus-reader-agent-opus-medium_20261024-185917: Daedalus - reader agent (opus, medium) 62.6% version 0.1.0; unvalidated, Andrii Pytel Oct 2026 Official leaderboard
69 CADGenBench submission andrii-pytel_daedalus-phased-pipeline-opus-medium-fin_20261018-191648: Daedalus - phased pipeline (opus, medium) - final r1 62.1% version 0.1.0; unvalidated, Andrii Pytel Oct 2026 Official leaderboard
70 CADGenBench submission cadse_baseline-v3-full-run-v2-27-editing-input_20261112-130649: baseline v3: full run v2 + 27 editing inputs unchanged (no-op floor), Opus xhigh, shift 0.7 % on generation only 61.9% version 0.1.0; unvalidated, CADSE Nov 2026 Official leaderboard
71 CADGenBench submission saysolid-adapted-hub-llc_saysolid-gpt-6-astra-edits-gpt-5-6-sol-e_20260916-012742: SaySolid gpt-6-astra (edits gpt-5.6-sol) exact-dataset-native-inputs worker ce6aa3128893 61.5% version 0.1.0; unvalidated, SaySolid / Adapted Hub LLC Sep 2026 Official leaderboard
72 CADGenBench submission saysolid-adapted-hub-llc_saysolid-claude-opus-5-5-exact-dataset-n_20261013-180006: SaySolid claude-opus-5-5 exact-dataset-native-inputs worker d9fd87a7c343 61.3% version 0.1.0; unvalidated, SaySolid / Adapted Hub LLC Oct 2026 Official leaderboard
73 CADGenBench submission saysolid-adapted-hub-llc_saysolid-gpt-6-1-sol-exact-dataset-nativ_20260930-020419: SaySolid gpt-6.1-sol exact-dataset-native-inputs worker 672ab9a3732b 61.2% version 0.1.0; unvalidated, SaySolid / Adapted Hub LLC Sep 2026 Official leaderboard
74 CADGenBench submission saysolid-adapted-hub-llc_saysolid-gpt-6-1-sol-exact-dataset-nativ_20261023-192958: SaySolid gpt-6.1-sol exact-dataset-native-inputs worker 682232c8535e 61.1% version 0.1.0; unvalidated, SaySolid / Adapted Hub LLC Oct 2026 Official leaderboard
75 CADGenBench submission nik6_nik6-harness-c-v1_20260816-183610: nik6-harness-c-v1 61.1% version 0.1.0; unvalidated, Nik6 Aug 2026 Official leaderboard
76 CADGenBench submission andrii-pytel_daedalus-reader-wholesheet-ablation-opus_20261024-230348: daedalus-reader-wholesheet-ablation-opus-medium 60.1% version 0.1.0; unvalidated, Andrii Pytel Oct 2026 Official leaderboard
77 CADGenBench submission saysolid-adapted-hub-llc_saysolid-gpt-6-1-sol-exact-dataset-nativ_20261008-110521: SaySolid gpt-6.1-sol exact-dataset-native-inputs worker 04d40445ddc3 60% version 0.1.0; unvalidated, SaySolid / Adapted Hub LLC Oct 2026 Official leaderboard
78 CADGenBench submission saysolid-adapted-hub-llc_saysolid-gpt-6-1-sol-exact-dataset-nativ_20261104-222118: SaySolid gpt-6.1-sol exact-dataset-native-inputs worker 545fa00b8179 59.9% version 0.1.0; unvalidated, SaySolid / Adapted Hub LLC Nov 2026 Official leaderboard
79 CADGenBench submission andrii-pytel_daedalus-phased-pipeline-opus-medium_20261024-185836: Daedalus - phased pipeline (opus, medium) 59.3% version 0.1.0; unvalidated, Andrii Pytel Oct 2026 Official leaderboard
80 CADGenBench submission matthew-lieb_cadi-generation-and-editing-2026-09-19_20260920-153059: CADI generation and editing, 2026-09-19 58.7% version 0.1.0; unvalidated, Matthew Lieb Sep 2026 Official leaderboard
81 CADGenBench submission pzfreo_build123d-mcp-0-3-84-dev0-gemini-3-8-fla_20260904-032010: build123d-mcp-0.3.84.dev0-gemini-3.8-flash-high-repair-first-complete81-r2 57.9% version 0.1.0; unvalidated, pzfreo Sep 2026 Official leaderboard
82 CADGenBench submission rexl2018_vextor-vxl-agent-engine-4cd1e674-r2_20261102-163559: Vextor VXL agent (engine 4cd1e674, r2) 57.5% version 0.1.0; unvalidated, rexl2018 Nov 2026 Official leaderboard
83 CADGenBench submission xueqinglin_openai-gpt-5-6-sol-claude-code-20260827-_20260827-063801: openai.gpt-5.6-sol_claude-code_20260827-114734 57.5% version 0.1.0; unvalidated, xueqinglin Aug 2026 Official leaderboard
84 CADGenBench submission nik6_nik6-cadgenbench-v1_20260808-223843: nik6-cadgenbench-v1 57.4% version 0.1.0; unvalidated, Nik6 Aug 2026 Official leaderboard
85 CADGenBench submission nik6_nik6-cadgenbench-v1_20260808-231147: nik6-cadgenbench-v1 57.4% version 0.1.0; unvalidated, Nik6 Aug 2026 Official leaderboard
86 CADGenBench submission rexl2018_vextor-vxl-agent-engine-4cd1e674_20261102-150618: Vextor VXL agent (engine 4cd1e674) 57.3% version 0.1.0; unvalidated, rexl2018 Nov 2026 Official leaderboard
87 CADGenBench submission nik6_nik6-harness-v8-v1_20260831-043302: nik6-harness-v8-v1 56.9% version 0.1.0; unvalidated, Nik6 Aug 2026 Official leaderboard
88 CADGenBench submission pzfreo_build123d-mcp-0-3-84-dev0-gemini-3-8-fla_20260904-034650: build123d-mcp-0.3.84.dev0-gemini-3.8-flash-high-recognition-execution-gen-dev388-complete81-r2 56.6% version 0.1.0; unvalidated, pzfreo Sep 2026 Official leaderboard
89 CADGenBench submission pzfreo_build123d-mcp-0-3-84-dev388-gemini-3-8-f_20260903-075326: build123d-mcp-0.3.84.dev388-gemini-3.8-flash-high 56.1% version 0.1.0; unvalidated, pzfreo Sep 2026 Official leaderboard
90 CADGenBench submission pzfreo_build123d-mcp-0-3-84-dev0-gemini-3-8-fla_20260903-141226: build123d-mcp-0.3.84.dev0-gemini-3.8-flash-high-recognition-forced-editing-gen-dev388-complete81-r1 55.9% version 0.1.0; unvalidated, pzfreo Sep 2026 Official leaderboard
91 CADGenBench submission xueqinglin_claude-opus-5-claude-code-20260825-17400_20260825-095149: claude-opus-5_claude-code_20260825-174002 55.8% version 0.1.0; unvalidated, xueqinglin Aug 2026 Official leaderboard
92 CADGenBench submission experiment_experiment_20260923-134635: Experiment 55.7% version 0.1.0; unvalidated, Experiment Sep 2026 Official leaderboard
93 CADGenBench submission saysolid-adapted-hub-llc_saysolid-gpt-6-astra-exact-dataset-nativ_20260905-170835: SaySolid gpt-6-astra exact-dataset-native-inputs worker f4566f7b5661 55% version 0.1.0; unvalidated, SaySolid / Adapted Hub LLC Sep 2026 Official leaderboard
94 CADGenBench submission b-rat_agent-cad-harness-claude-fable-5-1-gen49_20261012-002331: agent-cad harness / Claude Fable 5.1 (gen49 + edit32) 54.9% version 0.1.0; unvalidated, b-rat Oct 2026 Official leaderboard
95 CADGenBench submission andrii-pytel_daedalus-single-react-agent-opus-medium_20261004-190209: Daedalus - single ReAct agent (opus, medium) 54.4% version 0.1.0; unvalidated, Andrii Pytel Oct 2026 Official leaderboard
96 CADGenBench submission xueqinglin_openai-gpt-5-6-sol-baseline-20260826-193_20260826-115643: openai.gpt-5.6-sol_baseline_20260826-193928 53.9% version 0.1.0; unvalidated, xueqinglin Aug 2026 Official leaderboard
97 CADGenBench submission cadgenbench-2d-to-3d_gpt-6-1-sol-agentic-baseline_20261012-111954: gpt-6.1-sol agentic baseline 53.7% version 0.1.0; unvalidated, cadgenbench-2d-to-3d Oct 2026 Official leaderboard
98 CADGenBench submission andrii-pytel_daedalus-single-react-agent-opus-medium-_20261017-111238: Daedalus - single ReAct agent (opus, medium) - run 3 53.3% version 0.1.0; unvalidated, Andrii Pytel Oct 2026 Official leaderboard
99 CADGenBench submission pzfreo_gpt-5-6-sol-xhigh-floor-chain-v0379_20260717-045810: gpt-5.6-sol-xhigh-floor-chain-v0379 53.2% version 0.1.0; validated, pzfreo Jul 2026 Official leaderboard
100 CADGenBench submission andrii-pytel_daedalus-single-react-agent-opus-medium-_20261017-105639: Daedalus - single ReAct agent (opus, medium) - run 2 53% version 0.1.0; unvalidated, Andrii Pytel Oct 2026 Official leaderboard
101 CADGenBench submission mecado_grok-4-7-xhigh-mecado-baseline-with-buil_20260921-210958: Grok 4.7 xhigh Mecado Baseline with Build123d 52.1% version 0.1.0; unvalidated, Mecado Sep 2026 Official leaderboard
102 CADGenBench submission origogk_origogk-r24-convex-faces-remodels-108-11_20261019-142941: OrigoGK r24 convex faces + remodels 108 112 116 118 119 132 134 138 145 51.7% version 0.1.0; unvalidated, OrigoGK Oct 2026 Official leaderboard
103 CADGenBench submission cadse_brief-v7-full-run-49-generation-parts-op_20261112-180052: brief v7 full run, 49 generation parts, Opus builder 51.1% version 0.1.0; unvalidated, CADSE Nov 2026 Official leaderboard
104 CADGenBench submission pzfreo_build123d-mcp-0-3-83-gemini-flash-3-7_20260902-022750: build123d-mcp-0.3.83-gemini-flash-3.7 50.8% version 0.1.0; unvalidated, pzfreo Sep 2026 Official leaderboard
105 CADGenBench submission satvik-adyanthaya_archie-in-forge_20260711-184330: Archie in Forge 50.7% version 0.1.0; validated, Satvik Adyanthaya Jul 2026 Official leaderboard
106 CADGenBench submission anonymous_anonymous-agent_20260914-123111: Anonymous agent 50.6% version 0.1.0; unvalidated, Anonymous Sep 2026 Official leaderboard
107 CADGenBench submission anon-12345_generation-editing_20261015-144308: generation-editing 50.4% version 0.1.0; unvalidated, anon_12345 Oct 2026 Official leaderboard
108 CADGenBench submission experiment_experiment_20260822-234139: Experiment 49.8% version 0.1.0; unvalidated, Experiment Aug 2026 Official leaderboard
109 CADGenBench submission modelcorp_baseline-astra-codex-medium-single-sessi_20260904-202625: baseline_astra_codex_medium_single_session 49.8% version 0.1.0; unvalidated, modelcorp Sep 2026 Official leaderboard
110 CADGenBench submission modelcorp_baseline-astra-codex-sequential-pass_20260904-201609: baseline_astra_codex_sequential_pass 49.8% version 0.1.0; unvalidated, modelcorp Sep 2026 Official leaderboard
111 CADGenBench submission anonymous_anon-gen-1788896800-17b078_20260908-194644: anon-gen-1788896800-17b078 49.7% version 0.1.0; unvalidated, anonymous Sep 2026 Official leaderboard
112 CADGenBench submission mecado_grok-4-7-high-mecado-baseline-with-build_20260921-211028: Grok 4.7 high Mecado Baseline with Build123d 49.6% version 0.1.0; unvalidated, Mecado Sep 2026 Official leaderboard
113 CADGenBench submission cadse_full-run-v2-49-parts-all-opus-xhigh-full_20261112-123301: full run v2: 49 parts, all Opus xhigh, full brief + principles + hole rules v2, shift 0.7 % 49.5% version 0.1.0; unvalidated, CADSE Nov 2026 Official leaderboard
114 CADGenBench submission anonymous_anon-gen-1789061429-b7ed34_20260910-175227: anon-gen-1789061429-b7ed34 49.5% version 0.1.0; unvalidated, anonymous Sep 2026 Official leaderboard
115 CADGenBench submission experiment_experiment_20260913-202641: Experiment 49.4% version 0.1.0; unvalidated, Experiment Sep 2026 Official leaderboard
116 CADGenBench submission xueqinglin_baseline-gpt-5-6-sol-build123d_20260819-035800: baseline_gpt-5.6-sol_build123d 49.4% version 0.1.0; unvalidated, xueqinglin Aug 2026 Official leaderboard
117 CADGenBench submission xueqinglin_baseline-gpt-5-6-sol-build123d_20260819-062918: baseline_gpt-5.6-sol_build123d 49.4% version 0.1.0; unvalidated, xueqinglin Aug 2026 Official leaderboard
118 CADGenBench submission anonymous_test-submission-format_20260904-192600: test_submission_format 49% version 0.1.0; unvalidated, anonymous Sep 2026 Official leaderboard
119 CADGenBench submission cadse_full-run-v1-49-parts-full-brief-principl_20261112-115103: full run v1: 49 parts, full brief + principles + hole rules v2, Opus builder (xhigh for 9 fixtures and 21 others), shift 0.7 % 48.6% version 0.1.0; unvalidated, CADSE Nov 2026 Official leaderboard
120 CADGenBench submission makinarocks_drawx-2d3d-v4-gpt-6-astra_20261025-100833: drawx 2d3d v4 (gpt-6-astra) 48.5% version 0.1.0; unvalidated, makinarocks Oct 2026 Official leaderboard
121 CADGenBench submission w1ne_kernelcad-dev-refresh-20261026_20261026-192821: kernelcad-dev-refresh-20261026 48.4% version 0.1.0; unvalidated, w1ne Oct 2026 Official leaderboard
122 CADGenBench submission anonymous_anonymous-agent_20260914-095345: Anonymous agent 48.4% version 0.1.0; unvalidated, Anonymous Sep 2026 Official leaderboard
123 CADGenBench submission anonymous_deskwright-gpt-5-5-xhigh-native-inline_20260830-182813: DeskWright GPT-5.5 xhigh native-inline 47.9% version 0.1.0; unvalidated, Anonymous Aug 2026 Official leaderboard
124 CADGenBench submission anon-12345_generation-editing_20261015-002847: generation-editing 47.6% version 0.1.0; unvalidated, anon_12345 Oct 2026 Official leaderboard
125 CADGenBench submission w1ne_kernelcad-7e9082ab-gpt-5-6-sol-xhigh_20261019-105100: kernelcad-7e9082ab-gpt-5.6-sol-xhigh 47.5% version 0.1.0; unvalidated, w1ne Oct 2026 Official leaderboard
126 CADGenBench submission saysolid-adapted-hub-llc_saysolid-gpt-6-astra-exact-dataset-nativ_20260914-192424: SaySolid gpt-6-astra exact-dataset-native-inputs generation-arm-only worker 08f43e775f98 47.4% version 0.1.0; unvalidated, SaySolid / Adapted Hub LLC Sep 2026 Official leaderboard
127 CADGenBench submission origogk_origogk-r23-simplified-export-remodels-1_20261004-210724: OrigoGK r23 simplified export + remodels 112 118 119 134 47% version 0.1.0; unvalidated, OrigoGK Oct 2026 Official leaderboard
128 CADGenBench submission anon-12345_generation-editing_20261013-140852: generation-editing 46.8% version 0.1.0; unvalidated, anon_12345 Oct 2026 Official leaderboard
129 CADGenBench submission xueqinglin_glm-5-3-flash-claude-code-20260908-22435_20260909-022803: glm-5.3-flash_claude-code_20260908-224350 46.7% version 0.1.0; unvalidated, xueqinglin Sep 2026 Official leaderboard
130 CADGenBench submission rouan_cadrs-claude-opus-5-5-mcp-hand-driven-r2_20261010-090115: cadrs + Claude Opus 5.5 (MCP, hand-driven) r2 46.7% version 0.1.0; unvalidated, Rouan Oct 2026 Official leaderboard
131 CADGenBench submission xueqinglin_claude-opus-5-baseline-20260820-194627_20260820-115133: claude-opus-5_baseline_20260820-194627 46.3% version 0.1.0; unvalidated, xueqinglin Aug 2026 Official leaderboard
132 CADGenBench submission pzfreo_gpt55-v0368-xhigh-full_20260706-050450: gpt55-v0368-xhigh-full 46.1% version 0.1.0; unvalidated, pzfreo Jul 2026 Official leaderboard
133 CADGenBench submission pzfreo_gpt55-v0366-xhigh-full-vtkfix_20260704-200116: gpt55-v0366-xhigh-full-vtkfix 46.1% version 0.1.0; unvalidated, pzfreo Jul 2026 Official leaderboard
134 CADGenBench submission pzfreo_pzfreo-gpt55-v0376-xhigh-full_20260709-181849: pzfreo-gpt55-v0376-xhigh-full 46% version 0.1.0; unvalidated, pzfreo Jul 2026 Official leaderboard
135 CADGenBench submission makinarocks_drawx-2d3d-v4-gpt-6-1-sol_20261025-051216: drawx 2d3d v4 (gpt-6.1-sol) 45.8% version 0.1.0; unvalidated, makinarocks Oct 2026 Official leaderboard
136 CADGenBench submission pzfreo_gpt-5-5-build123d-mcp-0-3-59-xhigh-r5_20260627-141619: gpt-5.5-build123d-mcp-0.3.59-xhigh-r5 45.7% version 0.1.0; validated, pzfreo Jun 2026 Official leaderboard
137 CADGenBench submission xueqinglin_openai-gpt-5-6-sol-claude-code-20260825-_20260825-055902: openai.gpt-5.6-sol_claude-code_20260825-114538 45.5% version 0.1.0; unvalidated, xueqinglin Aug 2026 Official leaderboard
138 CADGenBench submission andrii-pytel_daedalus-one-shot-script-opus-medium-run_20261017-111400: Daedalus - one-shot script (opus, medium) - run 3 45.4% version 0.1.0; unvalidated, Andrii Pytel Oct 2026 Official leaderboard
139 CADGenBench submission arche_smith_20260711-010918: Smith 45.3% version 0.1.0; unvalidated, Arche Jul 2026 Official leaderboard
140 CADGenBench submission pzfreo_gpt-5-5-b123d-mcp-0-3-59-xhigh-full-p1_20260701-223602: gpt-5.5-b123d-mcp-0.3.59-xhigh-full-P1 45.2% version 0.1.0; unvalidated, pzfreo Jul 2026 Official leaderboard
141 Claude Fable 5 45.1% HF baseline (Build123d) Jun 2026 Official leaderboard
142 CADGenBench submission jspark_gpt-5-6-sol-build123d-loop-2_20260824-032415: gpt-5.6-sol_build123d_loop_2 45% version 0.1.0; unvalidated, jspark Aug 2026 Official leaderboard
143 CADGenBench submission anon-12345_generation-editing_20261003-134956: generation-editing 45% version 0.1.0; unvalidated, anon_12345 Oct 2026 Official leaderboard
144 CADGenBench submission james-dillard_claude-opus-5-5-candidate-p-pi-harness-s_20261002-094853: Claude Opus 5.5 Candidate P (Pi harness, standard help, 2026-10-01) 44.7% version 0.1.0; unvalidated, James Dillard Oct 2026 Official leaderboard
145 CADGenBench submission pzfreo_gpt-5-5-build123d-mcp-0-3-57-xhigh_20260624-051501: gpt-5.5-build123d-mcp-0.3.57-xhigh 44.5% version 0.1.0; unvalidated, pzfreo Jun 2026 Official leaderboard
146 CADGenBench submission saysolid-adapted-hub-llc_saysolid-gpt-5-6-sol-exact-dataset-nativ_20260829-132038: SaySolid gpt-5.6-sol exact-dataset-native-inputs worker 4af68790c698 44.5% version 0.1.0; unvalidated, SaySolid / Adapted Hub LLC Aug 2026 Official leaderboard
147 CADGenBench submission xueqinglin_kimi-k3-claude-code-20260907-214127_20260908-125546: kimi-k3_claude-code_20260907-214127 44.4% version 0.1.0; unvalidated, xueqinglin Sep 2026 Official leaderboard
148 CADGenBench submission mecado_grok-4-6-high-mecado-baseline-with-build_20260813-210045: Grok 4.6 high Mecado Baseline with Build123d 44.4% version 0.1.0; validated, Mecado Aug 2026 Official leaderboard
149 CADGenBench submission pzfreo_gpt55-v0364-xhigh-full-verifyspec_20260704-055230: gpt55-v0364-xhigh-full-verifyspec 43.9% version 0.1.0; unvalidated, pzfreo Jul 2026 Official leaderboard
150 CADGenBench submission origogk_origogk-r22-edit-operators-208-217-218-2_20261004-051610: OrigoGK r22 edit operators 208 217 218 224 248 43.8% version 0.1.0; unvalidated, OrigoGK Oct 2026 Official leaderboard
151 CADGenBench submission daanderson_fs-mcp-fable-5-minimal-harness_20260706-113645: FS MCP - Fable 5 - Minimal Harness 43.6% version 0.1.0; unvalidated, daanderson Jul 2026 Official leaderboard
152 CADGenBench submission xueqinglin_dashscope-qwen3-8-max-baseline-20260820-_20260820-075059: dashscope.qwen3.8-max_baseline_20260820-152330 43.6% version 0.1.0; unvalidated, xueqinglin Aug 2026 Official leaderboard
153 CADGenBench submission andrii-pytel_daedalus-one-shot-script-opus-medium_20261004-184853: Daedalus - one-shot script (opus, medium) 43.6% version 0.1.0; unvalidated, Andrii Pytel Oct 2026 Official leaderboard
154 CADGenBench submission test-submission_browser-based-cad-agent-full-81-sample-r_20260904-223403: Browser-based CAD agent — full 81-sample run 43.6% version 0.1.0; unvalidated, Test submission Sep 2026 Official leaderboard
155 CADGenBench submission mecado_claude-opus-5-max-mecado-baseline-with-b_20260813-223230: Claude Opus 5 max Mecado Baseline with Build123d 43.2% version 0.1.0; validated, Mecado Aug 2026 Official leaderboard
156 CADGenBench submission xueqinglin_dashscope-qwen3-8-max-claude-code-202608_20260826-113028: dashscope.qwen3.8-max_claude-code_20260826-192133 43.2% version 0.1.0; unvalidated, xueqinglin Aug 2026 Official leaderboard
157 CADGenBench submission xueqinglin_openai-gpt-5-6-sol-baseline-20260820-184_20260820-112107: openai.gpt-5.6-sol_baseline_20260820-184227 43.1% version 0.1.0; unvalidated, xueqinglin Aug 2026 Official leaderboard
158 CADGenBench submission makinarocks_drawx-2d3d-v53-gpt-6-1-terra_20261027-061524: drawx 2d3d v53 (gpt-6.1-terra) 43% version 0.1.0; unvalidated, makinarocks Oct 2026 Official leaderboard
159 CADGenBench submission jspark_gpt-5-6-sol-build123d_20260717-074106: gpt-5.6-sol build123d 43% version 0.1.0; unvalidated, jspark Jul 2026 Official leaderboard
160 CADGenBench submission paul-fremantle-pzfreo_build123d-mcp-claude-opus-4-8-full-81-fi_20260621-073422: build123d-mcp + Claude Opus 4.8 (full, 81 fixtures) 42.8% version 0.1.0; validated, Paul Fremantle (pzfreo) Jun 2026 Official leaderboard
161 CADGenBench submission saysolid-adapted-hub-llc_saysolid-gpt-5-6-sol-exact-dataset-nativ_20260829-225405: SaySolid gpt-5.6-sol exact-dataset-native-inputs worker 4af68790c698 42.7% version 0.1.0; unvalidated, SaySolid / Adapted Hub LLC Aug 2026 Official leaderboard
162 CADGenBench submission pzfreo_claude-opus-4-8-build123d-mcp-0-3-56_20260622-220357: claude-opus-4.8-build123d-mcp-0.3.56 42.7% version 0.1.0; unvalidated, pzfreo Jun 2026 Official leaderboard
163 CADGenBench submission pzfreo_pzfreo_20260622-205211: pzfreo 42.7% version 0.1.0; unvalidated, pzfreo Jun 2026 Official leaderboard
164 CADGenBench submission saysolid-adapted-hub-llc_saysolid-gpt-5-6-sol-exact-dataset-nativ_20260902-143854: SaySolid gpt-5.6-sol exact-dataset-native-inputs worker 364c948f664d 42.5% version 0.1.0; unvalidated, SaySolid / Adapted Hub LLC Sep 2026 Official leaderboard
165 CADGenBench submission rouan_cadrs-claude-opus-5-5-mcp-hand-driven_20261010-040826: cadrs + Claude Opus 5.5 (MCP, hand-driven) 42.5% version 0.1.0; unvalidated, Rouan Oct 2026 Official leaderboard
166 CADGenBench submission mecado_grok-4-6-xhigh-mecado-baseline-with-buil_20260813-215410: Grok 4.6 xhigh Mecado Baseline with Build123d 42.4% version 0.1.0; validated, Mecado Aug 2026 Official leaderboard
167 CADGenBench submission saysolid-adapted-hub-llc_saysolid-gpt-5-6-sol-exact-dataset-nativ_20260829-181641: SaySolid gpt-5.6-sol exact-dataset-native-inputs worker 4af68790c698 42.3% version 0.1.0; unvalidated, SaySolid / Adapted Hub LLC Aug 2026 Official leaderboard
168 CADGenBench submission saysolid-adapted-hub-llc_saysolid-gpt-5-6-sol-exact-dataset-nativ_20260829-080934: SaySolid gpt-5.6-sol exact-dataset-native-inputs worker 464ef83f8531 42.3% version 0.1.0; unvalidated, SaySolid / Adapted Hub LLC Aug 2026 Official leaderboard
169 CADGenBench submission pzfreo_gpt-5-6-sol-medium-mcp-0-3-78_20260711-055408: gpt-5.6-sol-medium-mcp-0.3.78 42.1% version 0.1.0; unvalidated, pzfreo Jul 2026 Official leaderboard
170 CADGenBench submission andrii-pytel_daedalus-one-shot-script-opus-medium-run_20261017-111318: Daedalus - one-shot script (opus, medium) - run 2 42% version 0.1.0; unvalidated, Andrii Pytel Oct 2026 Official leaderboard
171 CADGenBench submission xueqinglin_openai-gpt-5-6-sol-baseline-20260825-111_20260825-033327: openai.gpt-5.6-sol_baseline_20260825-111524 41.5% version 0.1.0; unvalidated, xueqinglin Aug 2026 Official leaderboard
172 CADGenBench submission mecado_gpt-5-6-sol-xhigh-mecado-baseline-with-b_20260813-233018: GPT-5.6 Sol xhigh Mecado Baseline with Build123d 41.2% version 0.1.0; validated, Mecado Aug 2026 Official leaderboard
173 CADGenBench submission pzfreo_gpt-5-5-build123d-mcp-0-3-56-v2_20260623-161750: gpt-5.5-build123d-mcp-0.3.56-v2 41.1% version 0.1.0; validated, pzfreo Jun 2026 Official leaderboard
174 CADGenBench submission pzfreo_gpt-5-5-build123d-mcp-0-3-59-medium-r2_20260627-143151: gpt-5.5-build123d-mcp-0.3.59-medium-r2 41.1% version 0.1.0; unvalidated, pzfreo Jun 2026 Official leaderboard
175 CADGenBench submission michaelr27_gpt-5-6-sol-hf-baseline-with-build123d_20260713-183956: GPT-5.6 Sol HF Baseline with Build123d 41.1% version 0.1.0; validated, michaelr27 Jul 2026 Official leaderboard
176 CADGenBench submission saysolid-adapted-hub-llc_saysolid-gpt-5-6-sol-exact-dataset-nativ_20260902-063145: SaySolid gpt-5.6-sol exact-dataset-native-inputs worker 364c948f664d 40.8% version 0.1.0; unvalidated, SaySolid / Adapted Hub LLC Sep 2026 Official leaderboard
177 CADGenBench submission anonymous_anon-gen-1788841910-f09d41_20260908-043152: anon-gen-1788841910-f09d41 40.8% version 0.1.0; unvalidated, anonymous Sep 2026 Official leaderboard
178 CADGenBench submission bolev-mikhail_b2c-opus5-finish-v2-gen49_20260916-113951: b2c-opus5-finish-v2-gen49 40.7% version 0.1.0; unvalidated, Bolev Mikhail Sep 2026 Official leaderboard
179 CADGenBench submission dani2l_build123d-mcp-0-3-91-sonnet-5-5_20261029-043937: build123d-mcp-0.3.91-sonnet-5.5 40.6% version 0.1.0; unvalidated, Dani2l Oct 2026 Official leaderboard
180 CADGenBench submission anon-12345_generation_20260930-134942: generation 40.5% version 0.1.0; unvalidated, anon_12345 Sep 2026 Official leaderboard
181 CADGenBench submission saysolid-adapted-hub-llc_saysolid-gpt-5-6-sol-exact-dataset-nativ_20260902-201006: SaySolid gpt-5.6-sol exact-dataset-native-inputs worker 364c948f664d 40.2% version 0.1.0; unvalidated, SaySolid / Adapted Hub LLC Sep 2026 Official leaderboard
182 CADGenBench submission origogk_origogk-r21-pinched-sliver-repair-240_20261001-033654: OrigoGK r21 pinched sliver repair 240 40.2% version 0.1.0; unvalidated, OrigoGK Oct 2026 Official leaderboard
183 CADGenBench submission jspark_gpt-5-6-sol-cadquery-max-iter5_20260712-145235: gpt-5.6-sol cadquery max-iter5 39.8% version 0.1.0; unvalidated, jspark Jul 2026 Official leaderboard
184 CADGenBench submission origogk_origogk-r20-face-extrusions-209-211-240_20261001-021200: OrigoGK r20 face extrusions 209 211 240 39.5% version 0.1.0; unvalidated, OrigoGK Oct 2026 Official leaderboard
185 CADGenBench submission anonymous_anon-gen-1787944336-7ffd_20260828-191217: anon-gen-1787944336-7ffd 39.4% version 0.1.0; unvalidated, anonymous Aug 2026 Official leaderboard
186 CADGenBench submission anonymous_anon-gen-1787928380-e027_20260828-144621: anon-gen-1787928380-e027 39.4% version 0.1.0; unvalidated, anonymous Aug 2026 Official leaderboard
187 CADGenBench submission anon-12345_generation_20260929-041603: generation 39.1% version 0.1.0; unvalidated, anon_12345 Sep 2026 Official leaderboard
188 CADGenBench submission unifyh_opus-48-toy-plugin-run4_20260709-031252: opus-48-toy-plugin-run4 38.8% version 0.1.0; unvalidated, unifyh Jul 2026 Official leaderboard
189 GPT-5.5 Pro 38.7% HF baseline (Build123d) Apr 2026 Official leaderboard
190 CADGenBench submission jselstad_opus-4-8-claude-code-text-to-cad-skill_20260618-075019: Opus 4.8 — Claude Code + text-to-cad skill 38.7% version 0.1.0; validated, jselstad Jun 2026 Official leaderboard
191 CADGenBench submission anonymous_anon-gen-1787893554-7a60_20260828-050555: anon-gen-1787893554-7a60 38.2% version 0.1.0; unvalidated, anonymous Aug 2026 Official leaderboard
192 CADGenBench submission origogk_origogk-r19-hole-removal-205_20260930-125014: OrigoGK r19 hole removal 205 37.9% version 0.1.0; unvalidated, OrigoGK Sep 2026 Official leaderboard
193 CADGenBench submission arche_smith_20260710-221438: Smith 37.8% version 0.1.0; unvalidated, Arche Jul 2026 Official leaderboard
194 CADGenBench submission anonymous_anon-gen-1787884326-48c4_20260828-023207: anon-gen-1787884326-48c4 37.6% version 0.1.0; unvalidated, anonymous Aug 2026 Official leaderboard
195 CADGenBench submission anonymous_anon-gen-1787868852-149a_20260827-221413: anon-gen-1787868852-149a 37.5% version 0.1.0; unvalidated, anonymous Aug 2026 Official leaderboard
196 CADGenBench submission mecado_grok-4-5-high-mecado-baseline-with-build_20260813-203342: Grok 4.5 high Mecado Baseline with Build123d 37% version 0.1.0; unvalidated, Mecado Aug 2026 Official leaderboard
197 Claude Opus 4.7 36.9% HF baseline (Build123d) Apr 2026 Official leaderboard
198 CADGenBench submission min-liu_chamfer-cad-agent-from-smartai_20260705-213856: Chamfer-CAD agent from SmartAI 36.8% version 0.1.0; unvalidated, Min Liu Jul 2026 Official leaderboard
199 CADGenBench submission test_test-submission_20260702-031247: test submission 36.7% version 0.1.0; unvalidated, test Jul 2026 Official leaderboard
200 CADGenBench submission bolev-mikhail_b2c-opus5-tools-gen49_20260910-122220: b2c-opus5-tools-gen49 36.7% version 0.1.0; unvalidated, Bolev Mikhail Sep 2026 Official leaderboard
201 CADGenBench submission origogk_origogk-r15-sliver-repair-250_20260930-105932: OrigoGK r15 sliver repair 250 36.6% version 0.1.0; unvalidated, OrigoGK Sep 2026 Official leaderboard
202 CADGenBench submission jselstad_opus-4-8-claude-code-build123d-mcp_20260618-080918: Opus 4.8 — Claude Code + build123d-mcp 36.4% version 0.1.0; unvalidated, jselstad Jun 2026 Official leaderboard
203 CADGenBench submission anon-12345_generation_20260928-152617: generation 36.4% version 0.1.0; unvalidated, anon_12345 Sep 2026 Official leaderboard
204 GPT-5.5 36% HF baseline (Build123d) Apr 2026 Official leaderboard
205 CADGenBench submission unifyh_opus-48-toy-plugin-run3_20260703-060749: opus-48-toy-plugin-run3 35.9% version 0.1.0; unvalidated, unifyh Jul 2026 Official leaderboard
206 CADGenBench submission unifyh_opus-48-toy-plugin-run2_20260703-024748: opus-48-toy-plugin-run2 35.9% version 0.1.0; unvalidated, unifyh Jul 2026 Official leaderboard
207 CADGenBench submission chow_20260902-114129-muse-spark-full_20260903-154026: 20260902_114129_muse-spark_full 35.8% version 0.1.0; unvalidated, chow Sep 2026 Official leaderboard
208 CADGenBench submission anonymous_anon-gen-1787797492-bb9e_20260827-022453: anon-gen-1787797492-bb9e 35.8% version 0.1.0; unvalidated, anonymous Aug 2026 Official leaderboard
209 CADGenBench submission origogk_origogk-r14-face-offsets-231-250_20260930-100641: OrigoGK r14 face offsets 231 250 35.7% version 0.1.0; unvalidated, OrigoGK Sep 2026 Official leaderboard
210 CADGenBench submission nataliya-shakhovska_daedalus-a4h-nogate-opus55-medium-r1_20261111-115811: daedalus-a4h-nogate-opus55-medium-r1 35.3% version 0.1.0; unvalidated, Nataliya Shakhovska Nov 2026 Official leaderboard
211 CADGenBench submission nataliya-shakhovska_daedalus-a4h-nogate-opus55-medium-r3_20261112-145445: daedalus-a4h-nogate-opus55-medium-r3 35.2% version 0.1.0; unvalidated, Nataliya Shakhovska Nov 2026 Official leaderboard
212 CADGenBench submission nrocketmann_glm-5-3-max-agentic-cad-zcode-subagents-_20260903-065136: GLM-5.3-Max agentic CAD (ZCode subagents, build123d) 35.1% version 0.1.0; unvalidated, nrocketmann Sep 2026 Official leaderboard
213 CADGenBench submission jselstad_opus-4-8-claude-code-basic-no-mcp-skill_20260618-071847: Opus 4.8 — Claude Code (basic, no MCP/skill) 34.9% version 0.1.0; unvalidated, jselstad Jun 2026 Official leaderboard
214 CADGenBench submission reckless-lampshade-230826_gpt-5-6-combined-best-generation_20260823-174609: gpt 5.6 combined best generation 34.6% version 0.1.0; unvalidated, reckless_lampshade_230826 Aug 2026 Official leaderboard
215 CADGenBench submission nataliya-shakhovska_daedalus-a4h-notable-opus55-medium-r1_20261111-123643: daedalus-a4h-notable-opus55-medium-r1 34.6% version 0.1.0; unvalidated, Nataliya Shakhovska Nov 2026 Official leaderboard
216 Claude Opus 4.8 34.5% HF baseline (Build123d) May 2026 Official leaderboard
217 CADGenBench submission origogk_origogk-r13-partial-238-thickness-edit_20260930-050126: OrigoGK r13 partial 238 thickness edit 34.5% version 0.1.0; unvalidated, OrigoGK Sep 2026 Official leaderboard
218 CADGenBench submission nataliya-shakhovska_daedalus-a4h-nogate-opus55-medium-r2_20261112-144806: daedalus-a4h-nogate-opus55-medium-r2 34.4% version 0.1.0; unvalidated, Nataliya Shakhovska Nov 2026 Official leaderboard
219 CADGenBench submission shashwatsaxena136_opus-4-8-build123d-baseline-full-81_20260615-171912: Opus 4.8 build123d baseline (full 81) 34.3% version 0.1.0; unvalidated, shashwatsaxena136 Jun 2026 Official leaderboard
220 CADGenBench submission pzfreo_build123d-mcp-0-3-90-gemini-4-argon-high_20261022-124342: build123d-mcp-0.3.90-gemini-4-argon-high 34.2% version 0.1.0; unvalidated, pzfreo Oct 2026 Official leaderboard
221 CADGenBench submission james-dillard_gpt-6-luna-candidate-n-pi-harness-five-s_20261002-094803: GPT-6 Luna Candidate N (Pi harness, five-stage workflow, 2026-10-01) 34% version 0.1.0; unvalidated, James Dillard Oct 2026 Official leaderboard
222 CADGenBench submission nataliya-shakhovska_daedalus-a4h-notable-opus55-medium-r3_20261112-145541: daedalus-a4h-notable-opus55-medium-r3 34% version 0.1.0; unvalidated, Nataliya Shakhovska Nov 2026 Official leaderboard
223 CADGenBench submission origogk_origogk-r12-remove-faces-edit-128-closed_20260930-033916: OrigoGK r12 remove-faces edit + 128 closed slots 34% version 0.1.0; unvalidated, OrigoGK Sep 2026 Official leaderboard
224 CADGenBench submission jselstad_opus-4-8-claude-code-build123d-mcp_20260617-144101: Opus 4.8 — Claude Code + build123d-mcp 33.9% version 0.1.0; unvalidated, jselstad Jun 2026 Official leaderboard
225 CADGenBench submission gpt-code_glm-5-3-flash-cadgenbench-baseline_20260831-100955: GLM-5.3-Flash CADGenBench baseline 33.9% version 0.1.0; unvalidated, gpt-code Aug 2026 Official leaderboard
226 CADGenBench submission hermes-agent_cadqueryskills-hermes-gpt-5-6-luna_20260921-191629: CadQuerySkills + Hermes + GPT-5.6-Luna 33.9% version 0.1.0; unvalidated, Hermes Agent Sep 2026 Official leaderboard
227 CADGenBench submission nataliya-shakhovska_daedalus-a4h-notable-opus55-medium-r2_20261112-145255: daedalus-a4h-notable-opus55-medium-r2 33.7% version 0.1.0; unvalidated, Nataliya Shakhovska Nov 2026 Official leaderboard
228 CADGenBench submission fuhao_opencode-qwen3-8-max-2d-to-3d-plugin-0-7_20261108-070837: opencode + qwen3.8-max · 2d-to-3d plugin 0.7.7.2-dev3 33.5% version 0.1.0; unvalidated, Fuhao Nov 2026 Official leaderboard
229 CADGenBench submission fuhao_opencode-qwen3-8-max-baseline-no-plugin_20261108-065450: opencode + qwen3.8-max · baseline (no plugin) 33% version 0.1.0; unvalidated, Fuhao Nov 2026 Official leaderboard
230 CADGenBench submission anonymous_anon-gen-1787778946-d6ad_20260826-211548: anon-gen-1787778946-d6ad 32.9% version 0.1.0; unvalidated, anonymous Aug 2026 Official leaderboard
231 CADGenBench submission james-dillard_gpt-6-luna-candidate-m-pi-harness-contro_20261002-094716: GPT-6 Luna Candidate M (Pi harness, control help, 2026-10-01) 32.9% version 0.1.0; unvalidated, James Dillard Oct 2026 Official leaderboard
232 CADGenBench submission james-dillard_gpt-5-6-sol-candidate-g-pi-harness-2026-_20260831-091037: GPT-5.6 Sol Candidate G (Pi harness, 2026-08-28) 32.9% version 0.1.0; unvalidated, James Dillard Aug 2026 Official leaderboard
233 CADGenBench submission shean-rahman_kinth-cadgenbench-full-gpt-5-5-retry-3_20260630-181939: Kinth CADGenBench full gpt-5.5 retry 3 32.8% version 0.1.0; unvalidated, Shean Rahman Jun 2026 Official leaderboard
234 CADGenBench submission origogk_origogk-r10-sparse-first-voxel-fallback_20260930-011452: OrigoGK r10 sparse-first voxel-fallback 32.8% version 0.1.0; unvalidated, OrigoGK Sep 2026 Official leaderboard
235 CADGenBench submission james-dillard_gpt-5-6-sol-candidate-f-pi-harness-2026-_20260831-091039: GPT-5.6 Sol Candidate F (Pi harness, 2026-08-28) 32.7% version 0.1.0; unvalidated, James Dillard Aug 2026 Official leaderboard
236 CADGenBench submission origogk_origogk-r11-128-drawn-diameter-source_20260930-015114: OrigoGK r11 128 drawn-diameter source 32.6% version 0.1.0; unvalidated, OrigoGK Sep 2026 Official leaderboard
237 CADGenBench submission james-dillard_gpt-5-6-sol-candidate-i-pi-harness-2026-_20260901-211012: GPT-5.6 Sol Candidate I (Pi harness, 2026-09-01) 32.3% version 0.1.0; unvalidated, James Dillard Sep 2026 Official leaderboard
238 CADGenBench submission origogk_origogk-r9-voxel-first-sliver-free_20260929-235952: OrigoGK r9 voxel-first sliver-free 32.2% version 0.1.0; unvalidated, OrigoGK Sep 2026 Official leaderboard
239 CADGenBench submission jselstad_opus-4-8-claude-code-basic-no-mcp-skill_20260617-141618: Opus 4.8 — Claude Code (basic, no MCP/skill) 32.2% version 0.1.0; unvalidated, jselstad Jun 2026 Official leaderboard
240 CADGenBench submission anon-120824_gpt-5-6_20260812-043905: gpt 5.6 31.6% version 0.1.0; unvalidated, anon_120824 Aug 2026 Official leaderboard
241 CADGenBench submission origogk_origogk-r7-reviewed-sources_20260929-233435: OrigoGK r7 reviewed-sources 31.2% version 0.1.0; unvalidated, OrigoGK Sep 2026 Official leaderboard
242 CADGenBench submission origogk_origogk-r8-voxel-first_20260929-234724: OrigoGK r8 voxel-first 31.1% version 0.1.0; unvalidated, OrigoGK Sep 2026 Official leaderboard
243 Gemini 3.1 Pro 31.1% HF baseline (Build123d) Feb 2026 Official leaderboard
244 Claude Opus 4.6 30.9% HF baseline (Build123d) Feb 2026 Official leaderboard
245 CADGenBench submission rakshit-dwivedi_proxima_20260903-035049: Proxima 30.8% version 0.1.0; unvalidated, Rakshit Dwivedi Sep 2026 Official leaderboard
246 CADGenBench submission nataliya-shakhovska_daedalus-a4h-whole-opus55-medium-r2_20261112-150703: daedalus-a4h-whole-opus55-medium-r2 30.7% version 0.1.0; unvalidated, Nataliya Shakhovska Nov 2026 Official leaderboard
247 CADGenBench submission mliu_chamfer-cad-harness-0-1-1_20260707-033749: chamfer-cad-harness-0.1.1 30.5% version 0.1.0; unvalidated, mliu Jul 2026 Official leaderboard
248 CADGenBench submission brambling_brambling_20260909-045047: brambling 30.5% version 0.1.0; unvalidated, brambling Sep 2026 Official leaderboard
249 CADGenBench submission anon-233107_eval-b12_20260912-051712: eval-b12 30.4% version 0.1.0; unvalidated, anon_233107 Sep 2026 Official leaderboard
250 CADGenBench submission saysolid-adapted-hub-llc_saysolid-gpt-5-6-luna-exact-dataset-nati_20260826-080728: SaySolid gpt-5.6-luna exact-dataset-native-inputs worker 41bd4d911831 30.2% version 0.1.0; unvalidated, SaySolid / Adapted Hub LLC Aug 2026 Official leaderboard
251 CADGenBench submission tharun-arety_cadrig-alpha_20260917-211434: CADRIG Alpha 30% version 0.1.0; unvalidated, Tharun Arety Sep 2026 Official leaderboard
252 CADGenBench submission cadsmith42_fable-5-1-agentic-editing-v2_20260913-185705: fable-5-1-agentic-editing-v2 30% version 0.1.0; unvalidated, cadsmith42 Sep 2026 Official leaderboard
253 CADGenBench submission nataliya-shakhovska_daedalus-a4h-whole-opus55-medium-r3_20261112-150821: daedalus-a4h-whole-opus55-medium-r3 30% version 0.1.0; unvalidated, Nataliya Shakhovska Nov 2026 Official leaderboard
254 CADGenBench submission anonymous_anon-edit-1787880475-69c8_20260828-012758: anon-edit-1787880475-69c8 29.9% version 0.1.0; unvalidated, anonymous Aug 2026 Official leaderboard
255 CADGenBench submission xueqinglin_dashscope-qwen3-8-max-claude-code-202608_20260825-110841: dashscope.qwen3.8-max_claude-code_20260825-190219 29.8% version 0.1.0; unvalidated, xueqinglin Aug 2026 Official leaderboard
256 CADGenBench submission nataliya-shakhovska_daedalus-a4h-whole-opus55-medium-r1_20261111-153840: daedalus-a4h-whole-opus55-medium-r1 29.8% version 0.1.0; unvalidated, Nataliya Shakhovska Nov 2026 Official leaderboard
257 CADGenBench submission tomuiv_mad-deepseek-v4-1-flash-baseline_20261003-120717: MAD DeepSeek-V4.1-Flash baseline 29.7% version 0.1.0; unvalidated, tomuiv Oct 2026 Official leaderboard
258 CADGenBench submission phi-linh_cad-gen-v4_20260817-150126: cad-gen v4 29.7% version 0.1.0; unvalidated, Phi Linh Aug 2026 Official leaderboard
259 CADGenBench submission saysolid-adapted-hub-llc_saysolid-gpt-5-6-sol-exact-dataset-nativ_20260826-002817: SaySolid gpt-5.6-sol exact-dataset-native-inputs worker 41bd4d911831 29.7% version 0.1.0; unvalidated, SaySolid / Adapted Hub LLC Aug 2026 Official leaderboard
260 CADGenBench submission pzfreo_gpt-5-5-build123d-mcp-0-3-56-partial61of_20260623-111130: gpt-5.5-build123d-mcp-0.3.56-partial61of81 29.6% version 0.1.0; unvalidated, pzfreo Jun 2026 Official leaderboard
261 CADGenBench submission origogk_origogk-r6-source-fix-edge-budget_20260929-170942: OrigoGK r6 source-fix edge-budget 29.6% version 0.1.0; unvalidated, OrigoGK Sep 2026 Official leaderboard
262 CADGenBench submission pimbs_pimbsv1_20260901-191627: Pimbsv1 29.6% version 0.1.0; unvalidated, Pimbs Sep 2026 Official leaderboard
263 CADGenBench submission anonymous_anon-edit-1787868057-f965_20260827-220059: anon-edit-1787868057-f965 29.5% version 0.1.0; unvalidated, anonymous Aug 2026 Official leaderboard
264 CADGenBench submission feral-teapot-230826_gpt-5-6_20260823-154940: gpt 5.6 29.4% version 0.1.0; unvalidated, feral_teapot_230826 Aug 2026 Official leaderboard
265 CADGenBench submission origogk_origogk-full-denominator-automatic-run-2_20260927-125419: OrigoGK full denominator automatic run 20260927 29.4% version 0.1.0; unvalidated, OrigoGK Sep 2026 Official leaderboard
266 CADGenBench submission anonymous_o-a1-1-f_20261021-142015: O-A1-1_f 29.2% version 0.1.0; unvalidated, Anonymous Oct 2026 Official leaderboard
267 CADGenBench submission anon-224918_sweep-g_20260911-054807: sweep-g 28.9% version 0.1.0; unvalidated, anon_224918 Sep 2026 Official leaderboard
268 CADGenBench submission andrii-pytel_daedalus-single-react-agent-opus-medium_20261003-215209: Daedalus - single ReAct agent (opus, medium) 28.7% version 0.1.0; unvalidated, Andrii Pytel Oct 2026 Official leaderboard
269 CADGenBench submission anonymous_anon-edit-1787797485-f5ff_20260827-022447: anon-edit-1787797485-f5ff 28.7% version 0.1.0; unvalidated, anonymous Aug 2026 Official leaderboard
270 CADGenBench submission anonymous_anon-edit-1787780317-d743_20260826-213840: anon-edit-1787780317-d743 28.6% version 0.1.0; unvalidated, anonymous Aug 2026 Official leaderboard
271 CADGenBench submission daanderson_fsmcp-opus-4-8_20260616-114515: FSMCP+Opus 4.8 28.5% version 0.1.0; unvalidated, daanderson Jun 2026 Official leaderboard
272 CADGenBench submission quartz17_quartz17_20260909-013330: quartz17 28.5% version 0.1.0; unvalidated, quartz17 Sep 2026 Official leaderboard
273 CADGenBench submission arche_smith_20260702-225821: Smith 28.3% version 0.1.0; unvalidated, Arche Jul 2026 Official leaderboard
274 CADGenBench submission anonymous_anon-edi-1788896801-b000c8_20260908-194649: anon-edi-1788896801-b000c8 28.3% version 0.1.0; unvalidated, anonymous Sep 2026 Official leaderboard
275 Claude Sonnet 4.6 28.3% HF baseline (Build123d) Feb 2026 Official leaderboard
276 CADGenBench submission joveh67_horu-8108_20261013-193641: horu-8108 28.3% version 0.1.0; unvalidated, joveh67 Oct 2026 Official leaderboard
277 CADGenBench submission metax_qwen-38-local-agent-union-73-81_20261012-063726: qwen-38 local agent (union 73/81) 28% version 0.1.0; unvalidated, metax Oct 2026 Official leaderboard
278 CADGenBench submission andrii-pytel_daedalus-phased-pipeline-opus-medium_20261004-083406: Daedalus - phased pipeline (opus, medium) 27.9% version 0.1.0; unvalidated, Andrii Pytel Oct 2026 Official leaderboard
279 CADGenBench submission saysolid-adapted-hub-llc_saysolid-kimi-k3-exact-dataset-native-in_20260827-183525: SaySolid kimi-k3 exact-dataset-native-inputs worker 3d74eda951f1 27.9% version 0.1.0; unvalidated, SaySolid / Adapted Hub LLC Aug 2026 Official leaderboard
280 CADGenBench submission cal-b_cal-b_20260908-204810: cal-b 27.7% version 0.1.0; unvalidated, cal-b Sep 2026 Official leaderboard
281 CADGenBench submission anonymous_anon-edi-1788841924-317e2e_20260908-043208: anon-edi-1788841924-317e2e 27.6% version 0.1.0; unvalidated, anonymous Sep 2026 Official leaderboard
282 CADGenBench submission anonymous_g5b_20261026-140509: G5b 27.6% version 0.1.0; unvalidated, Anonymous Oct 2026 Official leaderboard
283 CADGenBench submission tohom76_lakare-6523_20261013-193625: lakare-6523 27.6% version 0.1.0; unvalidated, tohom76 Oct 2026 Official leaderboard
284 CADGenBench submission cadsmith42_fable-5-1-agentic-editing_20260913-081127: fable-5-1-agentic-editing 27.3% version 0.1.0; unvalidated, cadsmith42 Sep 2026 Official leaderboard
285 CADGenBench submission hureho60_zuniri-4618_20261013-193655: zuniri-4618 27.2% version 0.1.0; unvalidated, hureho60 Oct 2026 Official leaderboard
286 CADGenBench submission anonymous_run-d_20261030-132414: Run D 27.2% version 0.1.0; unvalidated, Anonymous Oct 2026 Official leaderboard
287 CADGenBench submission anonymous_run-j_20261106-092634: Run J 27.1% version 0.1.0; unvalidated, Anonymous Nov 2026 Official leaderboard
288 CADGenBench submission anonymous_o_20261108-175622: O 26.9% version 0.1.0; unvalidated, Anonymous Nov 2026 Official leaderboard
289 CADGenBench submission anonymous_test-submission_20260821-191118: test-submission 26.9% version 0.1.0; unvalidated, anonymous Aug 2026 Official leaderboard
290 CADGenBench submission origogk_origogk-r5-contact-zero-rigid-edit_20260929-152629: OrigoGK r5 contact-zero rigid-edit 26.8% version 0.1.0; unvalidated, OrigoGK Sep 2026 Official leaderboard
291 CADGenBench submission cal-a_cal-a_20260908-024134: cal-a 26.7% version 0.1.0; unvalidated, cal-a Sep 2026 Official leaderboard
292 CADGenBench submission anonymous_run-l_20261107-122243: Run L 26.7% version 0.1.0; unvalidated, Anonymous Nov 2026 Official leaderboard
293 CADGenBench submission saysolid-adapted-hub-llc_saysolid-gpt-5-6-terra-exact-dataset-nat_20260826-024740: SaySolid gpt-5.6-terra exact-dataset-native-inputs worker 41bd4d911831 26.6% version 0.1.0; unvalidated, SaySolid / Adapted Hub LLC Aug 2026 Official leaderboard
294 CADGenBench submission reify_reify-deepseek-low-asi-all-edit-32-01_20261026-082500: reify-deepseek-low-asi-all-edit-32-01 26.4% version 0.1.0; unvalidated, Reify Oct 2026 Official leaderboard
295 CADGenBench submission bruno-mutagent_mutagent-brepsmith-opus-5-xhigh-agentic-_20260828-132328: mutagent-brepsmith — Opus-5 xhigh agentic harness (editing-only) 26.4% version 0.1.0; unvalidated, bruno-mutagent Aug 2026 Official leaderboard
296 CADGenBench submission cadybara-benchmark_exp005-run003-100-plus-copied-200_20260614-191528: EXP005 RUN003 100 plus copied 200 26.2% version 0.1.0; unvalidated, Cadybara Benchmark Jun 2026 Official leaderboard
297 CADGenBench submission cadybara_exp005-run003-100-plus-copied-200_20260614-192416: EXP005 RUN003 100 plus copied 200 26.1% version 0.1.0; unvalidated, Cadybara Jun 2026 Official leaderboard
298 CADGenBench submission andrii-pytel_daedalus-one-shot-script-opus-medium_20261003-215858: Daedalus - one-shot script (opus, medium) 26.1% version 0.1.0; unvalidated, Andrii Pytel Oct 2026 Official leaderboard
299 CADGenBench submission anonymous_run-g_20261105-082956: Run G 26% version 0.1.0; unvalidated, Anonymous Nov 2026 Official leaderboard
300 CADGenBench submission anonymous_cad-agent_20260821-172041: cad-agent 25.9% version 0.1.0; unvalidated, anonymous Aug 2026 Official leaderboard
301 CADGenBench submission origogk_origogk-bounded-surface-diagnostic_20260927-182738: OrigoGK bounded surface diagnostic 25.8% version 0.1.0; unvalidated, OrigoGK Sep 2026 Official leaderboard
302 CADGenBench submission origogk_origogk-planar-surface-diagnostic_20260927-160851: OrigoGK planar surface diagnostic 25.8% version 0.1.0; unvalidated, OrigoGK Sep 2026 Official leaderboard
303 CADGenBench submission origogk_origogk-surface-quality-diagnostic_20260927-221023: OrigoGK surface quality diagnostic 25.8% version 0.1.0; unvalidated, OrigoGK Sep 2026 Official leaderboard
304 CADGenBench submission w1ne_kernelcad-probe-genlane-v3-20261020_20261020-015604: kernelcad-probe-genlane-v3-20261020 25.7% version 0.1.0; unvalidated, w1ne Oct 2026 Official leaderboard
305 CADGenBench submission stealth_stealth-harness-haiku-5-5-xhigh_20261022-003154: Stealth Harness + Haiku 5.5 xHigh 25.6% version 0.1.0; unvalidated, Stealth Oct 2026 Official leaderboard
306 CADGenBench submission anonymous_run-f_20261103-081936: Run F 25.6% version 0.1.0; unvalidated, Anonymous Nov 2026 Official leaderboard
307 CADGenBench submission anonymous_v_20261110-144608: V 25.5% version 0.1.0; unvalidated, Anonymous Nov 2026 Official leaderboard
308 CADGenBench submission anonymous_run-h_20261105-161202: Run H 25.4% version 0.1.0; unvalidated, Anonymous Nov 2026 Official leaderboard
309 CADGenBench submission anonymous_p_20261109-044130: P 25.4% version 0.1.0; unvalidated, Anonymous Nov 2026 Official leaderboard
310 CADGenBench submission anonymous_run-i_20261106-041307: Run I 25.2% version 0.1.0; unvalidated, Anonymous Nov 2026 Official leaderboard
311 CADGenBench submission anonymous_v0-5_20261106-002457: v0.5 25.2% version 0.1.0; unvalidated, Anonymous Nov 2026 Official leaderboard
312 CADGenBench submission anonymous_q_20261109-090251: Q 25.2% version 0.1.0; unvalidated, Anonymous Nov 2026 Official leaderboard
313 CADGenBench submission origogk_origogk-retained-profile-surface-diagnos_20260927-050054: OrigoGK retained profile surface diagnostic 25% version 0.1.0; unvalidated, OrigoGK Sep 2026 Official leaderboard
314 Gemini 3.1 Flash-Lite 24.9% HF baseline (Build123d) Mar 2026 Official leaderboard
315 CADGenBench submission niziz67_homit-6594_20261007-061132: homit-6594 24.6% version 0.1.0; unvalidated, niziz67 Oct 2026 Official leaderboard
316 CADGenBench submission rakshit-dwivedi_proxima_20260902-200639: Proxima 24.6% version 0.1.0; unvalidated, Rakshit Dwivedi Sep 2026 Official leaderboard
317 CADGenBench submission james-dillard_gpt-5-nano-candidate-l-pi-harness-five-s_20261001-001100: GPT-5 Nano Candidate L (Pi harness, five-stage workflow, 2026-09-30) 24.5% version 0.1.0; unvalidated, James Dillard Oct 2026 Official leaderboard
318 CADGenBench submission anonymous_r_20261109-113330: R 24.3% version 0.1.0; unvalidated, Anonymous Nov 2026 Official leaderboard
319 CADGenBench submission origogk_origogk-axial-step-edit-215-diagnostic_20260926-161403: OrigoGK axial STEP edit 215 diagnostic 24% version 0.1.0; unvalidated, OrigoGK Sep 2026 Official leaderboard
320 CADGenBench submission anonymous_n_20261108-154638: N 23.9% version 0.1.0; unvalidated, Anonymous Nov 2026 Official leaderboard
321 CADGenBench submission miles-bimrose_qwen3-vl-235b-buil123d-ft-2stage_20260624-032814: Qwen3-VL-235B-buil123d-FT-2stage 23.8% version 0.1.0; unvalidated, Miles Bimrose Jun 2026 Official leaderboard
322 CADGenBench submission anonymous_m_20261108-125233: M 23.8% version 0.1.0; unvalidated, Anonymous Nov 2026 Official leaderboard
323 CADGenBench submission anonymous_lq-1_20261108-121453: LQ_1 23.7% version 0.1.0; unvalidated, Anonymous Nov 2026 Official leaderboard
324 CADGenBench submission local-user_t046-cgb-merge-101-150-mixed-v1_20261026-114525: t046-cgb-merge-101-150-mixed-v1 23.6% version 0.1.0; unvalidated, local-user Oct 2026 Official leaderboard
325 CADGenBench submission miles-bimrose_qwen3-vl-235b-build123d-v6-lora-ckpt-150_20260618-225130: Qwen3-VL-235B build123d v6 (LoRA ckpt-15000) 23.6% version 0.1.0; unvalidated, Miles Bimrose Jun 2026 Official leaderboard
326 CADGenBench submission jigem11_vomuko-4761_20261007-061022: vomuko-4761 23.6% version 0.1.0; unvalidated, jigem11 Oct 2026 Official leaderboard
327 CADGenBench submission anonymous_t_20261110-100802: T 23.5% version 0.1.0; unvalidated, Anonymous Nov 2026 Official leaderboard
328 CADGenBench submission anonymous_s_20261109-134515: S 23.4% version 0.1.0; unvalidated, Anonymous Nov 2026 Official leaderboard
329 CADGenBench submission xueqinglin_glm-5-2-baseline-20260820-170417_20260820-091506: glm-5.2_baseline_20260820-170417 23.4% version 0.1.0; unvalidated, xueqinglin Aug 2026 Official leaderboard
330 CADGenBench submission anonymous_run-e_20261030-134619: Run E 23.3% version 0.1.0; unvalidated, Anonymous Oct 2026 Official leaderboard
331 CADGenBench submission anonymous_run-k_20261106-221903: Run K 23.2% version 0.1.0; unvalidated, Anonymous Nov 2026 Official leaderboard
332 CADGenBench submission origogk_origogk-sparse-suite-diagnostic_20260926-145739: OrigoGK sparse suite diagnostic 22.9% version 0.1.0; unvalidated, OrigoGK Sep 2026 Official leaderboard
333 CADGenBench submission experiment_experiment_20260822-194005: Experiment 22.8% version 0.1.0; unvalidated, Experiment Aug 2026 Official leaderboard
334 CADGenBench submission anonymous_run-c_20261030-144138: Run C 22.7% version 0.1.0; unvalidated, Anonymous Oct 2026 Official leaderboard
335 CADGenBench submission feorka44_indoin-5234_20261006-210352: indoin-5234 22.6% version 0.1.0; unvalidated, feorka44 Oct 2026 Official leaderboard
336 CADGenBench submission anonymous_s46-a1_20261025-150639: S46-A1 22.5% version 0.1.0; unvalidated, Anonymous Oct 2026 Official leaderboard
337 CADGenBench submission anonymous_run-b_20261030-140256: Run B 22.5% version 0.1.0; unvalidated, Anonymous Oct 2026 Official leaderboard
338 CADGenBench submission anonymous_s45-a1_20261021-131325: S45-A1 22.5% version 0.1.0; unvalidated, Anonymous Oct 2026 Official leaderboard
339 CADGenBench submission arpado79_kaar-e88c_20261006-220543: kaar-e88c 22.1% version 0.1.0; unvalidated, arpado79 Oct 2026 Official leaderboard
340 CADGenBench submission ulwior35_givein-5069_20261006-213142: givein-5069 21.8% version 0.1.0; unvalidated, ulwior35 Oct 2026 Official leaderboard
341 CADGenBench submission miles-bimrose_qwen3-6-buil123d-ft-2stage_20260706-163128: Qwen3.6-buil123d-FT-2stage 21.7% version 0.1.0; unvalidated, Miles Bimrose Jul 2026 Official leaderboard
342 CADGenBench submission james-dillard_gpt-5-nano-candidate-k-pi-harness-contro_20261001-022034: GPT-5 Nano Candidate K (Pi harness, control help, 2026-09-30) 21.7% version 0.1.0; unvalidated, James Dillard Oct 2026 Official leaderboard
343 CADGenBench submission miles-bimrose_drmstep-hybrid-v5_20260628-062259: drmstep-hybrid-v5 21.6% version 0.1.0; unvalidated, Miles Bimrose Jun 2026 Official leaderboard
344 CADGenBench submission anonymous_u_20261110-121946: U 21.5% version 0.1.0; unvalidated, Anonymous Nov 2026 Official leaderboard
345 CADGenBench submission arche_smith_20260709-234450: Smith 21.4% version 0.1.0; unvalidated, Arche Jul 2026 Official leaderboard
346 CADGenBench submission arche_smith_20260624-022436: Smith 21.4% version 0.1.0; unvalidated, Arche Jun 2026 Official leaderboard
347 CADGenBench submission siwoh56_hesutu-6163_20261007-061147: hesutu-6163 21.4% version 0.1.0; unvalidated, siwoh56 Oct 2026 Official leaderboard
348 CADGenBench submission anonymous_w_20261112-070217: W 21.3% version 0.1.0; unvalidated, Anonymous Nov 2026 Official leaderboard
349 CADGenBench submission anonymous_sa-v2_20261025-224542: SA-V2 21.2% version 0.1.0; unvalidated, Anonymous Oct 2026 Official leaderboard
350 CADGenBench submission arche_smith_20260710-214646: Smith 20.9% version 0.1.0; unvalidated, Arche Jul 2026 Official leaderboard
351 CADGenBench submission saysolid-adapted-hub-llc_saysolid-gpt-6-astra-exact-dataset-nativ_20260914-205657: SaySolid gpt-6-astra exact-dataset-native-inputs editing-arm-only worker 46e6708c4207 20.9% version 0.1.0; unvalidated, SaySolid / Adapted Hub LLC Sep 2026 Official leaderboard
352 CADGenBench submission junde_junde-test_20260716-102222: junde-test 20.8% version 0.1.0; unvalidated, junde Jul 2026 Official leaderboard
353 CADGenBench submission anonymous_v0-9_20261106-002525: v0.9 20.4% version 0.1.0; unvalidated, Anonymous Nov 2026 Official leaderboard
354 CADGenBench submission anonymous_v0-2_20261105-153348: v0.2 20.4% version 0.1.0; unvalidated, Anonymous Nov 2026 Official leaderboard
355 CADGenBench submission anonymous_v0-7_20261106-002511: v0.7 20.4% version 0.1.0; unvalidated, Anonymous Nov 2026 Official leaderboard
356 CADGenBench submission anonymous_v0-4_20261105-153344: v0.4 20.1% version 0.1.0; unvalidated, Anonymous Nov 2026 Official leaderboard
357 CADGenBench submission anonymous_v0-3_20261105-153341: v0.3 20.1% version 0.1.0; unvalidated, Anonymous Nov 2026 Official leaderboard
358 CADGenBench submission bruno-mutagent_mutagent-brepsmith-sonnet-5-agentic-harn_20260827-080517: mutagent-brepsmith — Sonnet-5 agentic harness (editing-only) r3 20% version 0.1.0; unvalidated, bruno-mutagent Aug 2026 Official leaderboard
359 CADGenBench submission anon-170934_anon-170934_20260910-195151: anon_170934 19.9% version 0.1.0; unvalidated, anon_170934 Sep 2026 Official leaderboard
360 CADGenBench submission anonymous_anonymous-agent_20260917-082500: Anonymous agent 19.8% version 0.1.0; unvalidated, Anonymous Sep 2026 Official leaderboard
361 CADGenBench submission toparo-8937_gen17-toparo-8937_20261023-010520: gen17-toparo-8937 19.5% version 0.1.0; unvalidated, toparo-8937 Oct 2026 Official leaderboard
362 CADGenBench submission anonymous_v0-1_20261105-153003: v0.1 19.5% version 0.1.0; unvalidated, Anonymous Nov 2026 Official leaderboard
363 CADGenBench submission vasere-1792_gen17-vasere-1792_20261021-222031: gen17-vasere-1792 19.4% version 0.1.0; unvalidated, vasere-1792 Oct 2026 Official leaderboard
364 CADGenBench submission indian-peafowl_india_20260718-185300: India 19.2% version 0.1.0; unvalidated, Indian Peafowl Jul 2026 Official leaderboard
365 CADGenBench submission anonymous_anon-gen-1788819313-1f8489_20260907-221515: anon-gen-1788819313-1f8489 18.8% version 0.1.0; unvalidated, anonymous Sep 2026 Official leaderboard
366 CADGenBench submission anon-201155_sweep-e_20260910-210303: sweep-e 18.5% version 0.1.0; unvalidated, anon_201155 Sep 2026 Official leaderboard
367 CADGenBench submission james-dillard_gpt-5-nano-candidate-c-pi-harness-2026-0_20260828-001340: GPT-5 Nano Candidate C (Pi harness, 2026-08-27) 18.4% version 0.1.0; unvalidated, James Dillard Aug 2026 Official leaderboard
368 CADGenBench submission temape-4542_gen16-temape-4542_20261023-010547: gen16-temape-4542 18.4% version 0.1.0; unvalidated, temape-4542 Oct 2026 Official leaderboard
369 GLM-4.6V 18.3% HF baseline (Build123d) Dec 2025 Official leaderboard
370 CADGenBench submission gikabe-3612_gen16-gikabe-3612_20261021-221910: gen16-gikabe-3612 18.3% version 0.1.0; unvalidated, gikabe-3612 Oct 2026 Official leaderboard
371 CADGenBench submission cad-mcp-research_generation49-matched-evaluation-cell-248_20260824-080450: generation49 matched evaluation cell-2485f2e31202edef62dc 18.3% version 0.1.0; unvalidated, CAD-MCP Research Aug 2026 Official leaderboard
372 CADGenBench submission cad-mcp-research_baseline-protected-v0-7-11-all-generatio_20260824-183530: baseline-protected v0.7.11 all-generation CAD-MCP v0.7 18.1% version 0.1.0; unvalidated, CAD-MCP Research Aug 2026 Official leaderboard
373 CADGenBench submission origogk_origogk-sparse-suite-snapshot_20260926-142938: OrigoGK sparse suite snapshot 18% version 0.1.0; unvalidated, OrigoGK Sep 2026 Official leaderboard
374 CADGenBench submission anonymous_run-5f161034-1787724840_20260826-061750: run-5f161034-1787724840 18% version 0.1.0; unvalidated, anonymous Aug 2026 Official leaderboard
375 CADGenBench submission cad-mcp-research_baseline-protected-v0-7-11-all-generatio_20260824-182537: baseline-protected v0.7.11 all-generation Vanilla checkpoints 18% version 0.1.0; unvalidated, CAD-MCP Research Aug 2026 Official leaderboard
376 CADGenBench submission james-dillard_gpt-5-nano-candidate-j-pi-harness-2026-0_20260919-083944: GPT-5 Nano Candidate J (Pi harness, 2026-09-17) 17.6% version 0.1.0; unvalidated, James Dillard Sep 2026 Official leaderboard
377 CADGenBench submission giluze-5666_gen16-giluze-5666_20261022-184734: gen16-giluze-5666 17.6% version 0.1.0; unvalidated, giluze-5666 Oct 2026 Official leaderboard
378 CADGenBench submission cad-mcp-research_generation49-matched-evaluation-cell-8ee_20260824-081358: generation49 matched evaluation cell-8ee597dcef821bf18cf7 17.4% version 0.1.0; unvalidated, CAD-MCP Research Aug 2026 Official leaderboard
379 CADGenBench submission james-dillard_gpt-5-nano-candidate-e-pi-harness-2026-0_20260828-044843: GPT-5 Nano Candidate E (Pi harness, 2026-08-27) 17.3% version 0.1.0; unvalidated, James Dillard Aug 2026 Official leaderboard
380 CADGenBench submission anonymous_test-submission_20260819-015853: test-submission 17.2% version 0.1.0; unvalidated, anonymous Aug 2026 Official leaderboard
381 CADGenBench submission origogk_origogk-contact-fix-adaptive-step_20260929-101124: OrigoGK contact-fix adaptive-step 17.1% version 0.1.0; unvalidated, OrigoGK Sep 2026 Official leaderboard
382 CADGenBench submission arche_smith_20260709-222512: Smith 17.1% version 0.1.0; unvalidated, Arche Jul 2026 Official leaderboard
383 CADGenBench submission debumo-6710_gen16-debumo-6710_20261020-214856: gen16-debumo-6710 17% version 0.1.0; unvalidated, debumo-6710 Oct 2026 Official leaderboard
384 CADGenBench submission sibule-7638_gen16-sibule-7638_20261023-010458: gen16-sibule-7638 16.9% version 0.1.0; unvalidated, sibule-7638 Oct 2026 Official leaderboard
385 CADGenBench submission origogk_origogk-full-81-task-run-20260926_20260926-223823: OrigoGK full 81-task run 20260926 16.8% version 0.1.0; unvalidated, OrigoGK Sep 2026 Official leaderboard
386 CADGenBench submission gen-harness-b_gen-harness-b_20260910-195259: gen-harness-b 16.8% version 0.1.0; unvalidated, gen-harness-b Sep 2026 Official leaderboard
387 CADGenBench submission sesado-1438_gen16-sesado-1438_20261021-153018: gen16-sesado-1438 16.8% version 0.1.0; unvalidated, sesado-1438 Oct 2026 Official leaderboard
388 Qwen3-VL-235B-A22B-Instruct 16.8% HF baseline (Build123d) Sep 2025 Official leaderboard
389 CADGenBench submission yeshenpy_qwen-ablation_20260903-115457: Qwen ablation 16.7% version 0.1.0; unvalidated, yeshenpy Sep 2026 Official leaderboard
390 CADGenBench submission anonymous_o-a1_20261021-140503: O-A1 16.6% version 0.1.0; unvalidated, Anonymous Oct 2026 Official leaderboard
391 CADGenBench submission cad-mcp-blinded-study_cell-060ff6bdc2e19155fec8_20260821-084921: cell-060ff6bdc2e19155fec8 16.3% version 0.1.0; unvalidated, CAD-MCP blinded study Aug 2026 Official leaderboard
392 CADGenBench submission arche_smith_20260624-011205: Smith 16.3% version 0.1.0; unvalidated, Arche Jun 2026 Official leaderboard
393 CADGenBench submission baseline-v7_baseline-v7_20260910-195324: baseline-v7 16.3% version 0.1.0; unvalidated, baseline-v7 Sep 2026 Official leaderboard
394 CADGenBench submission cad-mcp-blinded-study_cell-04d75a55d41904fd073d_20260816-214010: cell-04d75a55d41904fd073d 16.2% version 0.1.0; unvalidated, CAD-MCP blinded study Aug 2026 Official leaderboard
395 CADGenBench submission yerin-choi_cad-mcp-paired-heldout-v1-vanilla-replic_20260814-143514: CAD-MCP paired heldout v1 vanilla replicate 3 16.1% version 0.1.0; unvalidated, Yerin Choi Aug 2026 Official leaderboard
396 CADGenBench submission cad-mcp-blinded-study_cell-08f852f7019f1b414b3a_20260821-085827: cell-08f852f7019f1b414b3a 16.1% version 0.1.0; unvalidated, CAD-MCP blinded study Aug 2026 Official leaderboard
397 CADGenBench submission experiment_experiment-partial-32-81-diagnostic_20260821-231550: Experiment - partial 32/81 diagnostic 16% version 0.1.0; unvalidated, Experiment Aug 2026 Official leaderboard
398 CADGenBench submission james-dillard_gpt-5-nano-candidate-h-pi-harness-2026-0_20260901-101026: GPT-5 Nano Candidate H (Pi harness, 2026-08-31) 15.8% version 0.1.0; unvalidated, James Dillard Sep 2026 Official leaderboard
399 CADGenBench submission cad-mcp-blinded-study_cell-1f61f132aa5bd4b4be8c_20260821-090655: cell-1f61f132aa5bd4b4be8c 15.8% version 0.1.0; unvalidated, CAD-MCP blinded study Aug 2026 Official leaderboard
400 CADGenBench submission rigazu-5835_edit16-rigazu-5835_20261030-011458: edit16-rigazu-5835 15.6% version 0.1.0; unvalidated, rigazu-5835 Oct 2026 Official leaderboard
401 CADGenBench submission yerin-choi_cad-mcp-paired-heldout-v1-cad-mcp-replic_20260814-143420: CAD-MCP paired heldout v1 cad_mcp replicate 2 15.6% version 0.1.0; unvalidated, Yerin Choi Aug 2026 Official leaderboard
402 CADGenBench submission local-user_codex-current-original-49-20261018-01_20261018-114008: codex-current-original-49-20261018-01 15.4% version 0.1.0; unvalidated, local-user Oct 2026 Official leaderboard
403 CADGenBench submission cad-mcp-blinded-study_cell-83efce1eb738ad54f712_20260821-091255: cell-83efce1eb738ad54f712 15.4% version 0.1.0; unvalidated, CAD-MCP blinded study Aug 2026 Official leaderboard
404 CADGenBench submission arche_smith_20260709-215857: Smith 15.4% version 0.1.0; unvalidated, Arche Jul 2026 Official leaderboard
405 CADGenBench submission cad-mcp-blinded-study_cell-92f624fa3400d7055063_20260816-220722: cell-92f624fa3400d7055063 15.3% version 0.1.0; unvalidated, CAD-MCP blinded study Aug 2026 Official leaderboard
406 CADGenBench submission yerin-choi_cad-mcp-paired-heldout-v1-vanilla-replic_20260814-143318: CAD-MCP paired heldout v1 vanilla replicate 2 15.3% version 0.1.0; unvalidated, Yerin Choi Aug 2026 Official leaderboard
407 CADGenBench submission ronado-1508_edit16-ronado-1508_20261024-154510: edit16-ronado-1508 15.3% version 0.1.0; unvalidated, ronado-1508 Oct 2026 Official leaderboard
408 CADGenBench submission goliki-7696_edit16-goliki-7696_20261024-154539: edit16-goliki-7696 15.2% version 0.1.0; unvalidated, goliki-7696 Oct 2026 Official leaderboard
409 CADGenBench submission cad-mcp-blinded-study_cell-f8302b92ab6b809510a9_20260821-092551: cell-f8302b92ab6b809510a9 15.1% version 0.1.0; unvalidated, CAD-MCP blinded study Aug 2026 Official leaderboard
410 CADGenBench submission huggingface_gpt-5-6-sol-hf-baseline-pipeline-test_20260807-094609: GPT-5.6 Sol HF Baseline (pipeline test) 15% version 0.1.0; unvalidated, HuggingFace Aug 2026 Official leaderboard
411 CADGenBench submission fefona-2711_edit16-fefona-2711_20261030-011434: edit16-fefona-2711 14.9% version 0.1.0; unvalidated, fefona-2711 Oct 2026 Official leaderboard
412 CADGenBench submission cad-mcp-blinded-study_cell-c9bba894d207e6be92fd_20260816-221300: cell-c9bba894d207e6be92fd 14.9% version 0.1.0; unvalidated, CAD-MCP blinded study Aug 2026 Official leaderboard
413 CADGenBench submission arche_smith_20260709-215034: Smith 14.8% version 0.1.0; unvalidated, Arche Jul 2026 Official leaderboard
414 CADGenBench submission yerin-choi_cad-mcp-paired-heldout-v1-cad-mcp-replic_20260814-143202: CAD-MCP paired heldout v1 cad_mcp replicate 1 14.8% version 0.1.0; unvalidated, Yerin Choi Aug 2026 Official leaderboard
415 CADGenBench submission cad-mcp-blinded-study_cell-4603538f259e6df50d72_20260816-215447: cell-4603538f259e6df50d72 14.7% version 0.1.0; unvalidated, CAD-MCP blinded study Aug 2026 Official leaderboard
416 CADGenBench submission yerin-choi_cad-mcp-paired-heldout-v1-vanilla-replic_20260814-142911: CAD-MCP paired heldout v1 vanilla replicate 1 14.6% version 0.1.0; unvalidated, Yerin Choi Aug 2026 Official leaderboard
417 CADGenBench submission daanderson_fsmcp-opus-4-8-stl_20260616-122528: FSMCP+Opus 4.8 - STL 14.6% version 0.1.0; unvalidated, daanderson Jun 2026 Official leaderboard
418 CADGenBench submission arche_smith_20260709-212542: Smith 14.4% version 0.1.0; unvalidated, Arche Jul 2026 Official leaderboard
419 CADGenBench submission cad-mcp-blinded-study_cell-85da63afedcb6c20f060_20260816-220149: cell-85da63afedcb6c20f060 14.3% version 0.1.0; unvalidated, CAD-MCP blinded study Aug 2026 Official leaderboard
420 CADGenBench submission yerin-choi_cad-mcp-paired-heldout-v1-cad-mcp-replic_20260814-143620: CAD-MCP paired heldout v1 cad_mcp replicate 3 14.2% version 0.1.0; unvalidated, Yerin Choi Aug 2026 Official leaderboard
421 CADGenBench submission anonymous_run-3283c228-1787609057_20260824-222220: run-3283c228-1787609057 14% version 0.1.0; unvalidated, anonymous Aug 2026 Official leaderboard
422 CADGenBench submission anonymous_run-3283c228-1787609057_20260824-232333: run-3283c228-1787609057 14% version 0.1.0; unvalidated, anonymous Aug 2026 Official leaderboard
423 CADGenBench submission cad-mcp-blinded-study_cell-329c6ab62a4397e86819_20260816-214811: cell-329c6ab62a4397e86819 13.9% version 0.1.0; unvalidated, CAD-MCP blinded study Aug 2026 Official leaderboard
424 CADGenBench submission cad-mcp-blinded-study_cell-d5fe8f58a164aa9aee2a_20260821-092007: cell-d5fe8f58a164aa9aee2a 13.7% version 0.1.0; unvalidated, CAD-MCP blinded study Aug 2026 Official leaderboard
425 CADGenBench submission anonymous_anon-edi-1788819332-ce4901_20260907-221535: anon-edi-1788819332-ce4901 13.5% version 0.1.0; unvalidated, anonymous Sep 2026 Official leaderboard
426 CADGenBench submission yeshenpy_a-r2_20260902-081542: A-r2 13.5% version 0.1.0; unvalidated, yeshenpy Sep 2026 Official leaderboard
427 CADGenBench submission anonymous_run-4934da30-1787675208_20260825-163254: run-4934da30-1787675208 13.4% version 0.1.0; unvalidated, anonymous Aug 2026 Official leaderboard
428 CADGenBench submission anonymous_run-5f161034-1787686551_20260825-193825: run-5f161034-1787686551 13.4% version 0.1.0; unvalidated, anonymous Aug 2026 Official leaderboard
429 CADGenBench submission anonymous_run-797978e8-1787636081_20260825-053639: run-797978e8-1787636081 12.5% version 0.1.0; unvalidated, anonymous Aug 2026 Official leaderboard
430 CADGenBench submission anonymous_run-ca7da17d-1787680716_20260825-180307: run-ca7da17d-1787680716 12.4% version 0.1.0; unvalidated, anonymous Aug 2026 Official leaderboard
431 CADGenBench submission anonymous_run-863e3c01-1788312265_20260902-012426: run-863e3c01-1788312265 12.4% version 0.1.0; unvalidated, anonymous Sep 2026 Official leaderboard
432 CADGenBench submission james-dillard_gpt-5-nano-candidate-a-pi-harness-2026-0_20260827-100706: GPT-5 Nano Candidate A (Pi harness, 2026-08-26) 12.4% version 0.1.0; unvalidated, James Dillard Aug 2026 Official leaderboard
433 CADGenBench submission phi-linh_cad-gen-gpt-5-mini-v1_20260713-215232: cad-gen gpt-5-mini v1 12.3% version 0.1.0; unvalidated, Phi Linh Jul 2026 Official leaderboard
434 CADGenBench submission phi-linh_cad-gen-gpt-5-mini-v1_20260713-215219: cad-gen gpt-5-mini v1 12.3% version 0.1.0; unvalidated, Phi Linh Jul 2026 Official leaderboard
435 CADGenBench submission anonymous_anonymous-agent_20260916-133147: Anonymous agent 12.3% version 0.1.0; unvalidated, Anonymous Sep 2026 Official leaderboard
436 CADGenBench submission anonymous_run-46e66701-1787624064_20260825-040828: run-46e66701-1787624064 12.2% version 0.1.0; unvalidated, anonymous Aug 2026 Official leaderboard
437 CADGenBench submission anonymous_run-8baebabe-1788313256_20260902-014057: run-8baebabe-1788313256 12% version 0.1.0; unvalidated, anonymous Sep 2026 Official leaderboard
438 CADGenBench submission arche_smith_20260708-000637: Smith 11.6% version 0.1.0; unvalidated, Arche Jul 2026 Official leaderboard
439 CADGenBench submission arche_smith_20260708-062950: Smith 11.5% version 0.1.0; unvalidated, Arche Jul 2026 Official leaderboard
440 CADGenBench submission anonymous_anonymous-agent_20260916-183114: Anonymous agent 11.4% version 0.1.0; unvalidated, Anonymous Sep 2026 Official leaderboard
441 CADGenBench submission arche_smith_20260708-065352: Smith 11.4% version 0.1.0; unvalidated, Arche Jul 2026 Official leaderboard
442 CADGenBench submission arche_smith_20260623-230519: Smith 11.4% version 0.1.0; unvalidated, Arche Jun 2026 Official leaderboard
443 CADGenBench submission arche_smith_20260624-001648: Smith 11.4% version 0.1.0; unvalidated, Arche Jun 2026 Official leaderboard
444 CADGenBench submission james-dillard_gpt-5-nano-candidate-d-pi-harness-2026-0_20260828-025518: GPT-5 Nano Candidate D (Pi harness, 2026-08-27) 10.9% version 0.1.0; unvalidated, James Dillard Aug 2026 Official leaderboard
445 CADGenBench submission yitong42_codex-gpt-5-6-sol-high-15-sample_20260811-162034: Codex + gpt-5.6-sol high (15-sample) 10.5% version 0.1.0; unvalidated, yitong42 Aug 2026 Official leaderboard
446 CADGenBench submission origogk_origogk-1mm-full-input-diagnostic_20260929-052612: OrigoGK 1mm full-input diagnostic 10.5% version 0.1.0; unvalidated, OrigoGK Sep 2026 Official leaderboard
447 CADGenBench submission cadse_brief-v7-fable-5-2-builder-effort-high-9_20261112-185357: brief v7, Fable 5.2 builder effort high, 9 fixtures (seed 20261112) 10.1% version 0.1.0; unvalidated, CADSE Nov 2026 Official leaderboard
448 CADGenBench submission anonymous_anon-gen-1788761670-72e736_20260907-061431: anon-gen-1788761670-72e736 9.92% version 0.1.0; unvalidated, anonymous Sep 2026 Official leaderboard
449 CADGenBench submission pave-cad_pave-cad-tool-assisted-no-skill-build123_20260712-165946: PAVE-CAD tool_assisted_no_skill_build123d.v2 (cadgenbench_langgraph_qwen37_plus_20260526) 9.86% version 0.1.0; unvalidated, PAVE-CAD Jul 2026 Official leaderboard
450 CADGenBench submission daanderson_fs-mcp-opus-4-8-minimal-harness_20260615-131636: FS MCP - Opus 4.8 - Minimal Harness 9.83% version 0.1.0; unvalidated, daanderson Jun 2026 Official leaderboard
451 CADGenBench submission cadse_review-arm-brief-v7-builds-after-blind-r_20261112-155250: Review arm: brief v7 builds after blind review and fix, nine fixtures 9.72% version 0.1.0; unvalidated, CADSE Nov 2026 Official leaderboard
452 CADGenBench submission cadse_small-offset-r7x-effort-xhigh-solids-shi_20261112-111053: small offset r7x: effort xhigh solids shifted by 0.7 % of the diagonal (alignment test), 9 random fixtures (seed 20261112) 9.68% version 0.1.0; unvalidated, CADSE Nov 2026 Official leaderboard
453 CADGenBench submission cadse_brief-v7-on-dyno-nine-fixtures-effort-ma_20261112-151818: Brief v7 on dyno: nine fixtures, effort max, one build per part 9.63% version 0.1.0; unvalidated, CADSE Nov 2026 Official leaderboard
454 CADGenBench submission timeci-8199_gen8-timeci-8199_20261018-155944: gen8-timeci-8199 9.50% version 0.1.0; unvalidated, timeci-8199 Oct 2026 Official leaderboard
455 CADGenBench submission miles-bimrose_qwen3-vl-8b-build123d-finetune_20260611-212111: Qwen3-VL-8B build123d finetune 9.42% version 0.1.0; unvalidated, Miles Bimrose Jun 2026 Official leaderboard
456 CADGenBench submission yitong42_pi-agent-gpt-5-6-sol-high-15-sample_20260811-164701: Pi Agent + gpt-5.6-sol high (15-sample) 9.27% version 0.1.0; unvalidated, yitong42 Aug 2026 Official leaderboard
457 CADGenBench submission cadse_effort-xhigh-r7x-full-brief-principles-h_20261112-095633: effort xhigh r7x: full brief + principles + hole rules v2, Opus builder, 9 random fixtures (seed 20261112) 9.26% version 0.1.0; unvalidated, CADSE Nov 2026 Official leaderboard
458 CADGenBench submission cadse_guarded-offset-r5-round-5-solids-shifted_20261112-093438: guarded offset r5: round 5 solids shifted 1.5 % unless near-symmetric (alignment test), 9 random fixtures (seed 20261112) 8.97% version 0.1.0; unvalidated, CADSE Nov 2026 Official leaderboard
459 CADGenBench submission cadse_small-offset-r5-round-5-solids-shifted-b_20261112-111149: small offset r5: round 5 solids shifted by 0.7 % of the diagonal (alignment test), 9 random fixtures (seed 20261112) 8.97% version 0.1.0; unvalidated, CADSE Nov 2026 Official leaderboard
460 CADGenBench submission cadse_pose-rotx-r5-round-5-solids-turned-180-d_20261112-090958: pose rotx r5: round 5 solids turned 180 deg about x (alignment test), 9 random fixtures (seed 20261112) 8.90% version 0.1.0; unvalidated, CADSE Nov 2026 Official leaderboard
461 CADGenBench submission pzfreo_build123d-mcp-0-3-85-dev0-gpt-6-astra-hi_20260905-060736: build123d-mcp-0.3.85.dev0-gpt-6-astra-high 8.84% version 0.1.0; unvalidated, pzfreo Sep 2026 Official leaderboard
462 CADGenBench submission james-dillard_gpt-5-nano-candidate-b-pi-harness-2026-0_20260827-101758: GPT-5 Nano Candidate B (Pi harness, 2026-08-26) 8.79% version 0.1.0; unvalidated, James Dillard Aug 2026 Official leaderboard
463 CADGenBench submission alexchunlin_claude-opus-5-5-blender-cadlib-drawing-t_20261027-223010: Claude Opus 5.5 + Blender/cadlib + drawing tools (OCR, measure, holes, overlay), faceted STEP (10-sample) 8.78% version 0.1.0; unvalidated, alexchunlin Oct 2026 Official leaderboard
464 CADGenBench submission cadse_small-offset-lean3-hole-rules-v2-lean-so_20261112-111231: small offset lean3: hole rules v2 lean solids shifted by 0.7 % of the diagonal (alignment test), 9 random fixtures (seed 20261112) 8.76% version 0.1.0; unvalidated, CADSE Nov 2026 Official leaderboard
465 CADGenBench submission cadse_small-offset-r6-round-6-solids-shifted-b_20261112-092806: small offset r6: round 6 solids shifted by 0.7 % of the diagonal (alignment test), 9 random fixtures (seed 20261112) 8.69% version 0.1.0; unvalidated, CADSE Nov 2026 Official leaderboard
466 CADGenBench submission cadse_economy-mode-off-buildbox-principles-v4-_20261112-071308: economy mode off: buildbox principles v4 + scoring-aware brief + zoom, Opus builder, 9 random fixtures (seed 20261112) 8.68% version 0.1.0; unvalidated, CADSE Nov 2026 Official leaderboard
467 CADGenBench submission cadse_offset-lean3-hole-rules-v2-lean-solids-s_20261112-090323: offset lean3: hole rules v2 lean solids shifted by 1.5 % of the diagonal (alignment test), 9 random fixtures (seed 20261112) 8.66% version 0.1.0; unvalidated, CADSE Nov 2026 Official leaderboard
468 CADGenBench submission origogk_origogk-generation-housing-diagnostic-20_20260926-060753: OrigoGK generation housing diagnostic 20260926 8.63% version 0.1.0; unvalidated, OrigoGK Sep 2026 Official leaderboard
469 CADGenBench submission alexchunlin_claude-opus-5-5-plain-build123d-10-sampl_20261027-144651: Claude Opus 5.5 + plain build123d (10-sample pilot, comparison arm) 8.63% version 0.1.0; unvalidated, alexchunlin Oct 2026 Official leaderboard
470 CADGenBench submission cadse_pose-rotz-r5-round-5-solids-turned-180-d_20261112-090903: pose rotz r5: round 5 solids turned 180 deg about z (alignment test), 9 random fixtures (seed 20261112) 8.63% version 0.1.0; unvalidated, CADSE Nov 2026 Official leaderboard
471 CADGenBench submission borisyich_freecad-mcp-v1-37-gpt-5-6-high-some_20260817-090235: freecad-mcp-v1.37-gpt-5.6-high-some 8.60% version 0.1.0; unvalidated, borisyich Aug 2026 Official leaderboard
472 CADGenBench submission cadse_offset-r6-round-6-solids-shifted-by-1-5-_20261112-090242: offset r6: round 6 solids shifted by 1.5 % of the diagonal (alignment test), 9 random fixtures (seed 20261112) 8.60% version 0.1.0; unvalidated, CADSE Nov 2026 Official leaderboard
473 CADGenBench submission cadse_pose-roty-r5-round-5-solids-turned-180-d_20261112-091042: pose roty r5: round 5 solids turned 180 deg about y (alignment test), 9 random fixtures (seed 20261112) 8.60% version 0.1.0; unvalidated, CADSE Nov 2026 Official leaderboard
474 CADGenBench submission cadse_round-6-full-brief-principles-hole-rules_20261112-083429: round 6: full brief + principles + hole rules v2, Opus builder, 9 random fixtures (seed 20261112) 8.36% version 0.1.0; unvalidated, CADSE Nov 2026 Official leaderboard
475 CADGenBench submission pzfreo_opus5-xhigh-official-baseline-prompt-nom_20260809-222310: opus5-xhigh-official-baseline-prompt-nomcp-partial11-r1 8.34% version 0.1.0; unvalidated, pzfreo Aug 2026 Official leaderboard
476 CADGenBench submission cadse_hole-rules-v2-lean-prompt-zoom-opus-buil_20261112-080413: hole rules v2: lean prompt + zoom, Opus builder, 9 random fixtures (seed 20261112) 8.31% version 0.1.0; unvalidated, CADSE Nov 2026 Official leaderboard
477 CADGenBench submission cadse_passage-and-hole-rules-lean-prompt-zoom-_20261112-072345: passage and hole rules: lean prompt + zoom, Opus builder, 9 random fixtures (seed 20261112) 8.18% version 0.1.0; unvalidated, CADSE Nov 2026 Official leaderboard
478 CADGenBench submission cadse_repeat-r5b-full-brief-principles-v4-unch_20261112-102013: repeat r5b: full brief + principles v4, unchanged repeat of round 5, Opus builder, 9 random fixtures (seed 20261112) 7.97% version 0.1.0; unvalidated, CADSE Nov 2026 Official leaderboard
479 CADGenBench submission alexchunlin_claude-opus-5-5-headless-blender-cadlib-_20261027-150637: Claude Opus 5.5 + headless Blender/cadlib, faceted STEP (10-sample pilot) 7.94% version 0.1.0; unvalidated, alexchunlin Oct 2026 Official leaderboard
480 CADGenBench submission alexchunlin_claude-opus-5-5-blender-cadlib-faceted-s_20261027-215115: Claude Opus 5.5 + Blender/cadlib, faceted STEP (10-sample repeat, no drawing tools) 7.87% version 0.1.0; unvalidated, alexchunlin Oct 2026 Official leaderboard
481 CADGenBench submission cadse_repeat-2-lean-prompt-no-principles-zoom-_20261112-071803: repeat 2: lean prompt (no principles) + zoom, Opus builder, 9 random fixtures (seed 20261112) 7.61% version 0.1.0; unvalidated, CADSE Nov 2026 Official leaderboard
482 CADGenBench submission petrichor_petrichor_20260909-071845: petrichor 7.56% version 0.1.0; unvalidated, petrichor Sep 2026 Official leaderboard
483 CADGenBench submission cadse_lean-prompt-no-principles-zoom-opus-buil_20261112-055409: lean prompt (no principles) + zoom, Opus builder, 9 random fixtures (seed 20261112) 7.51% version 0.1.0; unvalidated, CADSE Nov 2026 Official leaderboard
484 CADGenBench submission min-liu_chamfer-t1-edit-smoke15_20260709-013607: chamfer-t1-edit-smoke15 7.30% version 0.1.0; unvalidated, Min Liu Jul 2026 Official leaderboard
485 CADGenBench submission origogk_origogk-analytic-edits-diagnostic-202609_20260926-044655: OrigoGK analytic edits diagnostic 20260926 7.06% version 0.1.0; unvalidated, OrigoGK Sep 2026 Official leaderboard
486 CADGenBench submission cadse_sheet-notes-r1-full-brief-principles-bui_20261112-111817: sheet notes r1: full brief + principles + build123d sheet-metal notes, 7 sheet-metal parts only, Opus builder (seed 20261112) 6.79% version 0.1.0; unvalidated, CADSE Nov 2026 Official leaderboard
487 CADGenBench submission pzfreo_gpt-5-5-b123d-mcp-0-3-59-xhigh-smoke10-p_20260701-131749: gpt-5.5-b123d-mcp-0.3.59-xhigh-SMOKE10-P1 6.73% version 0.1.0; unvalidated, pzfreo Jul 2026 Official leaderboard
488 CADGenBench submission anon-181240_sweep-c2_20260910-202002: sweep-c2 6.66% version 0.1.0; unvalidated, anon_181240 Sep 2026 Official leaderboard
489 CADGenBench submission cadse_buildbox-principles-v3-compare-loop-opus_20261112-040654: buildbox principles v3 + compare loop, Opus builder, 9 random fixtures (seed 20261112) 6.63% version 0.1.0; unvalidated, CADSE Nov 2026 Official leaderboard
490 CADGenBench submission pzfreo_build123d-mcp-0-3-90-gemini-4-argon-high_20261021-205929: build123d-mcp-0.3.90-gemini-4-argon-high 6.51% version 0.1.0; unvalidated, pzfreo Oct 2026 Official leaderboard
491 CADGenBench submission cadse_buildbox-principles-v4-scoring-aware-bri_20261112-051241: buildbox principles v4 + scoring-aware brief + zoom, Opus builder, 9 random fixtures (seed 20261112) 6.43% version 0.1.0; unvalidated, CADSE Nov 2026 Official leaderboard
492 CADGenBench submission reify_reify-sol-low-asi-202-209-paired-01_20261021-220527: reify-sol-low-asi-202-209-paired-01 6.35% version 0.1.0; unvalidated, Reify Oct 2026 Official leaderboard
493 CADGenBench submission cadse_hand-edited-diagnostic-probes-on-3-fixtu_20261112-061555: hand-edited diagnostic probes on 3 fixtures (single change each), other 6 = earlier run r3 6.34% version 0.1.0; unvalidated, CADSE Nov 2026 Official leaderboard
494 CADGenBench submission cadse_buildbox-principles-v4-drawing-rules-com_20261112-043202: buildbox principles v4 (drawing rules) + compare loop, Opus builder, 9 random fixtures (seed 20261112) 6.25% version 0.1.0; unvalidated, CADSE Nov 2026 Official leaderboard
495 CADGenBench submission cadse_buildbox-principles-opus-builder-9-rando_20261112-033752: buildbox principles + Opus builder, 9 random fixtures (seed 20261112) 6.14% version 0.1.0; unvalidated, CADSE Nov 2026 Official leaderboard
496 CADGenBench submission pzfreo_build123d-mcp-0-3-83-fable-5-1-high_20260902-121723: build123d-mcp-0.3.83-fable-5.1-high 6.09% version 0.1.0; unvalidated, pzfreo Sep 2026 Official leaderboard
497 CADGenBench submission yitong42_matched-baseline-codex-gpt-5-6-sol-high-_20260906-170553: Matched baseline + Codex gpt-5.6-sol high (10-case) 6.08% version 0.1.0; unvalidated, yitong42 Sep 2026 Official leaderboard
498 CADGenBench submission lolopu-8948_edit8-lolopu-8948_20261030-011549: edit8-lolopu-8948 6.04% version 0.1.0; unvalidated, lolopu-8948 Oct 2026 Official leaderboard
499 CADGenBench submission local-user_t047-inspect-feedback-six-20261029_20261029-155032: t047-inspect-feedback-six-20261029 5.95% version 0.1.0; unvalidated, local-user Oct 2026 Official leaderboard
500 CADGenBench submission origogk_origogk-sparse-dual-full-input-diagnosti_20260928-160948: OrigoGK sparse-dual full-input diagnostic 5.91% version 0.1.0; unvalidated, OrigoGK Sep 2026 Official leaderboard
501 CADGenBench submission reify_reify-sol-low-naked-202-209-paired-01_20261021-220143: reify-sol-low-naked-202-209-paired-01 5.90% version 0.1.0; unvalidated, Reify Oct 2026 Official leaderboard
502 CADGenBench submission pzfreo_pzfreo_20260902-062348: pzfreo 5.83% version 0.1.0; unvalidated, pzfreo Sep 2026 Official leaderboard
503 CADGenBench submission yitong42_m2d-first-codex-gpt-5-6-sol-high-10-case_20260906-170530: M2D-first + Codex gpt-5.6-sol high (10-case) 5.82% version 0.1.0; unvalidated, yitong42 Sep 2026 Official leaderboard
504 CADGenBench submission local-user_t047-autonomous-feedback-six-20261030_20261030-010719: t047-autonomous-feedback-six-20261030 5.82% version 0.1.0; unvalidated, local-user Oct 2026 Official leaderboard
505 CADGenBench submission pzfreo_gpt55-v0368-smoke10_20260705-172407: gpt55-v0368-smoke10 5.81% version 0.1.0; unvalidated, pzfreo Jul 2026 Official leaderboard
506 CADGenBench submission pzfreo_gpt-5-5-b123d-mcp-0-3-59-xhigh-smoke10-n_20260627-171359: gpt-5.5-b123d-mcp-0.3.59-xhigh-SMOKE10-newprompt 5.75% version 0.1.0; unvalidated, pzfreo Jun 2026 Official leaderboard
507 CADGenBench submission reify_reify-deepseek-low-asi-217-238-01_20261023-070657: reify-deepseek-low-asi-217-238-01 5.70% version 0.1.0; unvalidated, Reify Oct 2026 Official leaderboard
508 CADGenBench submission cad-study_baseline-no-planning_20261007-140142: baseline-no_planning 5.65% version 0.1.0; unvalidated, CAD Study Oct 2026 Official leaderboard
509 CADGenBench submission anonymous_anon-gen-1788670318-98a7_20260906-045201: anon-gen-1788670318-98a7 5.64% version 0.1.0; unvalidated, anonymous Sep 2026 Official leaderboard
510 CADGenBench submission anonymous_anon-gen-1788746242-74b911_20260907-015723: anon-gen-1788746242-74b911 5.61% version 0.1.0; unvalidated, anonymous Sep 2026 Official leaderboard
511 CADGenBench submission anonymous_anon-gen-1788680583-e9d0_20260906-074305: anon-gen-1788680583-e9d0 5.48% version 0.1.0; unvalidated, anonymous Sep 2026 Official leaderboard
512 CADGenBench submission anonymous_anon-gen-1788717334-a056_20260906-175535: anon-gen-1788717334-a056 5.45% version 0.1.0; unvalidated, anonymous Sep 2026 Official leaderboard
513 CADGenBench submission pzfreo_agy-gemini37-flash-high-plan-mcp0383-smo_20260901-190641: agy-gemini37-flash-high-plan-mcp0383-smoke6 5.28% version 0.1.0; unvalidated, pzfreo Sep 2026 Official leaderboard
514 CADGenBench submission pzfreo_gpt55-pr40-pr403-smoke10_20260708-215753: gpt55-pr40-pr403-smoke10 5.24% version 0.1.0; unvalidated, pzfreo Jul 2026 Official leaderboard
515 CADGenBench submission local-user_t047-tool021-tx-a-20261029_20261029-060246: t047-tool021-tx-a-20261029 5.19% version 0.1.0; unvalidated, local-user Oct 2026 Official leaderboard
516 CADGenBench submission cad-study_baseline-graph-cad-planning_20261007-230611: baseline-graph_cad_planning 5.03% version 0.1.0; unvalidated, CAD Study Oct 2026 Official leaderboard
517 CADGenBench submission tamarind_tamarind_20260909-152727: tamarind 4.95% version 0.1.0; unvalidated, tamarind Sep 2026 Official leaderboard
518 CADGenBench submission anonymous_anon-edi-1788761677-0e4b7e_20260907-061438: anon-edi-1788761677-0e4b7e 4.89% version 0.1.0; unvalidated, anonymous Sep 2026 Official leaderboard
519 CADGenBench submission origogk_origogk-bounded-dual-full-input-diagnost_20260928-141343: OrigoGK bounded-dual full-input diagnostic 4.87% version 0.1.0; unvalidated, OrigoGK Sep 2026 Official leaderboard
520 CADGenBench submission cad-study_baseline-cadcoder-planning_20261007-193721: baseline-cadcoder_planning 4.81% version 0.1.0; unvalidated, CAD Study Oct 2026 Official leaderboard
521 CADGenBench submission pzfreo_pzfreo-gpt55-v0375-smoke10-mcp_20260709-104821: pzfreo_gpt55-v0375-smoke10-mcp 4.68% version 0.1.0; unvalidated, pzfreo Jul 2026 Official leaderboard
522 CADGenBench submission cad-study_baseline-general-coding-plan_20261007-174344: baseline-general_coding-plan 4.66% version 0.1.0; unvalidated, CAD Study Oct 2026 Official leaderboard
523 CADGenBench submission local-user_t047-r3-b-r01-20261027_20261027-081850: t047-r3-b-r01-20261027 4.62% version 0.1.0; unvalidated, local-user Oct 2026 Official leaderboard
524 CADGenBench submission cad-study_baseline-no-plan-rerun_20261008-045844: baseline_no_plan_rerun 4.61% version 0.1.0; unvalidated, CAD Study Oct 2026 Official leaderboard
525 CADGenBench submission reify_reify-deepseek-low-naked-217-238-paralle_20261023-030248: reify-deepseek-low-naked-217-238-parallel-01 4.59% version 0.1.0; unvalidated, Reify Oct 2026 Official leaderboard
526 CADGenBench submission pzfreo_fable5-v0360-med-eff-smoke5_20260702-042807: fable5-v0360-med-eff-smoke5 4.57% version 0.1.0; unvalidated, pzfreo Jul 2026 Official leaderboard
527 CADGenBench submission anonymous_anon-gen-1787740768-01a0_20260826-103929: anon-gen-1787740768-01a0 4.55% version 0.1.0; unvalidated, anonymous Aug 2026 Official leaderboard
528 CADGenBench submission yitong42_native-gpt-6-astra-ultra-baseline-4-case_20260917-050440: Native GPT-6 Astra Ultra baseline 4-case 20260916-235800 4.55% version 0.1.0; unvalidated, yitong42 Sep 2026 Official leaderboard
529 CADGenBench submission anonymous_anon-gen-1788675770-a7c0_20260906-062252: anon-gen-1788675770-a7c0 4.48% version 0.1.0; unvalidated, anonymous Sep 2026 Official leaderboard
530 CADGenBench submission pzfreo_build123d-mcp-0-3-84-dev0-gemini-3-8-fla_20260903-113023: build123d-mcp-0.3.84.dev0-gemini-3.8-flash-high-recognition-editing6-r2 4.46% version 0.1.0; unvalidated, pzfreo Sep 2026 Official leaderboard
531 CADGenBench submission yitong42_native-gpt-6-astra-ultra-svg-first-4-cas_20260917-050647: Native GPT-6 Astra Ultra svg-first 4-case 20260916-235800 4.41% version 0.1.0; unvalidated, yitong42 Sep 2026 Official leaderboard
532 CADGenBench submission reify_reify-sol-low-asi-217-238-parallel-01_20261023-030814: reify-sol-low-asi-217-238-parallel-01 4.37% version 0.1.0; unvalidated, Reify Oct 2026 Official leaderboard
533 CADGenBench submission cajuce-1755_gen4-cajuce-1755_20261017-164050: gen4-cajuce-1755 4.35% version 0.1.0; unvalidated, cajuce-1755 Oct 2026 Official leaderboard
534 CADGenBench submission miles-bimrose_qwen3-vl-2b-build123d-finetune_20260609-204140: Qwen3-VL-2B build123d finetune 4.34% version 0.1.0; unvalidated, Miles Bimrose Jun 2026 Official leaderboard
535 CADGenBench submission cad-study_baseline-no-planning-corrected_20261010-041632: baseline-no_planning_corrected 4.30% version 0.1.0; unvalidated, CAD Study Oct 2026 Official leaderboard
536 CADGenBench submission anonymous_anon-gen-1787964784-d19c_20260829-005305: anon-gen-1787964784-d19c 4.29% version 0.1.0; unvalidated, anonymous Aug 2026 Official leaderboard
537 CADGenBench submission anonymous_anon-gen-1787967441-5839_20260829-013722: anon-gen-1787967441-5839 4.29% version 0.1.0; unvalidated, anonymous Aug 2026 Official leaderboard
538 CADGenBench submission pzfreo_gpt-5-5-b123d-mcp-0-3-59-xhigh-resmoke7-_20260627-192314: gpt-5.5-b123d-mcp-0.3.59-xhigh-RESMOKE7-fixed 4.27% version 0.1.0; unvalidated, pzfreo Jun 2026 Official leaderboard
539 CADGenBench submission reify_reify-sol-low-asi-211-215-config-01_20261022-062053: reify-sol-low-asi-211-215-config-01 4.26% version 0.1.0; unvalidated, Reify Oct 2026 Official leaderboard
540 CADGenBench submission local-user_t047-full-mid-feedback-six-20261030_20261029-192823: t047-full-mid-feedback-six-20261030 4.13% version 0.1.0; unvalidated, local-user Oct 2026 Official leaderboard
541 CADGenBench submission pidebe-5079_gen4-pidebe-5079-r2_20261016-172912: gen4-pidebe-5079-r2 4.03% version 0.1.0; unvalidated, pidebe-5079 Oct 2026 Official leaderboard
542 CADGenBench submission anonymous_anon-gen-1788548779-3c7e_20260904-190620: anon-gen-1788548779-3c7e 3.94% version 0.1.0; unvalidated, anonymous Sep 2026 Official leaderboard
543 CADGenBench submission local-user_t047-0770-b-dev4-20261027_20261026-190236: t047-0770-B-dev4-20261027 3.87% version 0.1.0; unvalidated, local-user Oct 2026 Official leaderboard
544 CADGenBench submission anonymous_anon-gen-1789088535-1624c8_20260911-010919: anon-gen-1789088535-1624c8 3.84% version 0.1.0; unvalidated, anonymous Sep 2026 Official leaderboard
545 CADGenBench submission local-user_t047-0771-p-dev4-20261027_20261026-190417: t047-0771-P-dev4-20261027 3.80% version 0.1.0; unvalidated, local-user Oct 2026 Official leaderboard
546 CADGenBench submission origogk_origogk-native-triangle-kernel-diagnosti_20260928-114945: OrigoGK native-triangle kernel diagnostic 3.77% version 0.1.0; unvalidated, OrigoGK Sep 2026 Official leaderboard
547 CADGenBench submission local-user_t047-0771-p2-dev4-20261027_20261027-034922: t047-0771-P2-dev4-20261027 3.72% version 0.1.0; unvalidated, local-user Oct 2026 Official leaderboard
548 CADGenBench submission cadse_qwen3-8-flash-next-local-4-bit-thinking-_20261112-071939: Qwen3.8-Flash-Next (local, 4 bit, thinking on): lean prompt + API idioms + check loop, 9 random fixtures (seed 20261112) 3.69% version 0.1.0; unvalidated, CADSE Nov 2026 Official leaderboard
549 CADGenBench submission cadse_qwen3-8-flash-next-local-4-bit-thinking-_20261112-074554: Qwen3.8-Flash-Next (local, 4 bit, thinking on): principles text + API idioms + check loop, 9 random fixtures (seed 20261112) 3.60% version 0.1.0; unvalidated, CADSE Nov 2026 Official leaderboard
550 CADGenBench submission w1ne_kernelcad-probe-edit-v4-20261020_20261020-013517: kernelcad-probe-edit-v4-20261020 3.55% version 0.1.0; unvalidated, w1ne Oct 2026 Official leaderboard
551 CADGenBench submission pzfreo_opus5-xhigh-mcp-source-backed-sample6-r1_20260811-100624: opus5-xhigh-mcp-source-backed-sample6-r1 3.52% version 0.1.0; unvalidated, pzfreo Aug 2026 Official leaderboard
552 CADGenBench submission origogk_origogk-surface-bounds-same12-diagnostic_20260928-122509: OrigoGK surface-bounds same12 diagnostic 3.52% version 0.1.0; unvalidated, OrigoGK Sep 2026 Official leaderboard
553 CADGenBench submission cadse_flash-next-read-sheet-notes-read-then-co_20261112-135102: Flash-Next read + sheet notes: read-then-compare with sheet-metal notes on 108 and 114, 9 random fixtures (seed 20261112) 3.50% version 0.1.0; unvalidated, CADSE Nov 2026 Official leaderboard
554 CADGenBench submission anonymous_anon-edit-1788032760-be22_20260829-194601: anon-edit-1788032760-be22 3.48% version 0.1.0; unvalidated, anonymous Aug 2026 Official leaderboard
555 CADGenBench submission local-user_t047-r3-p2-r01-20261027_20261027-082316: t047-r3-p2-r01-20261027 3.43% version 0.1.0; unvalidated, local-user Oct 2026 Official leaderboard
556 CADGenBench submission cadse_flash-next-lean-r2-qwen3-8-flash-next-on_20261112-135027: Flash-Next lean r2: Qwen3.8-Flash-Next on Brev, thinking on, 12 rounds, 9 random fixtures (seed 20261112) 3.43% version 0.1.0; unvalidated, CADSE Nov 2026 Official leaderboard
557 CADGenBench submission pzfreo_opus5-xhigh-minimal-mcp-cross-sections-s_20260813-051907: opus5-xhigh-minimal-mcp-cross-sections-sample6-r4 3.41% version 0.1.0; unvalidated, pzfreo Aug 2026 Official leaderboard
558 CADGenBench submission cadse_flash-next-read-then-compare-qwen3-8-fla_20261112-134952: Flash-Next read-then-compare: Qwen3.8-Flash-Next on Brev, reads dimensions first and keeps the best-agreeing build, 9 random fixtures (seed 20261112) 3.35% version 0.1.0; unvalidated, CADSE Nov 2026 Official leaderboard
559 CADGenBench submission pzfreo_pzfreo-opus5-xhigh-mcp-fidelity-workflow_20260812-191538: pzfreo-opus5-xhigh-mcp-fidelity-workflow-fe01ca8-sample6-r1 3.30% version 0.1.0; unvalidated, pzfreo Aug 2026 Official leaderboard
560 CADGenBench submission local-user_t047-end-review-a-three-20261030_20261030-043124: t047-end-review-a-three-20261030 3.30% version 0.1.0; unvalidated, local-user Oct 2026 Official leaderboard
561 CADGenBench submission anonymous_anon-gen-1788389662-455b_20260902-225424: anon-gen-1788389662-455b 3.29% version 0.1.0; unvalidated, anonymous Sep 2026 Official leaderboard
562 CADGenBench submission anonymous_anon-gen-1788407486-cf7b_20260903-035127: anon-gen-1788407486-cf7b 3.29% version 0.1.0; unvalidated, anonymous Sep 2026 Official leaderboard
563 CADGenBench submission anonymous_run-y_20261112-115942: Run Y 3.25% version 0.1.0; unvalidated, Anonymous Nov 2026 Official leaderboard
564 CADGenBench submission anonymous_anon-gen-1788030000-4639_20260829-190002: anon-gen-1788030000-4639 3.24% version 0.1.0; unvalidated, anonymous Aug 2026 Official leaderboard
565 CADGenBench submission anonymous_ab_20261112-143821: AB 3.24% version 0.1.0; unvalidated, Anonymous Nov 2026 Official leaderboard
566 CADGenBench submission yitong42_svga-g-r1-gpt6-svg-gpt56-cad-840e3511902_20260928-042929: SVGA G-r1 GPT6 SVG GPT56 CAD 840e35119023 3.19% version 0.1.0; unvalidated, yitong42 Sep 2026 Official leaderboard
567 CADGenBench submission local-user_t051-r012-c-frozen-followup-20261103_20261103-144030: t051-r012-c-frozen-followup-20261103 3.19% version 0.1.0; unvalidated, local-user Nov 2026 Official leaderboard
568 CADGenBench submission anonymous_aa_20261112-135052: AA 3.19% version 0.1.0; unvalidated, Anonymous Nov 2026 Official leaderboard
569 CADGenBench submission anonymous_anon-gen-1788486936-fd25_20260904-015537: anon-gen-1788486936-fd25 3.14% version 0.1.0; unvalidated, anonymous Sep 2026 Official leaderboard
570 CADGenBench submission local-user_t047-tool021-tx-b-20261029_20261029-060423: t047-tool021-tx-b-20261029 3.14% version 0.1.0; unvalidated, local-user Oct 2026 Official leaderboard
571 CADGenBench submission anonymous_anon-gen-1788549253-6668_20260904-191414: anon-gen-1788549253-6668 3.12% version 0.1.0; unvalidated, anonymous Sep 2026 Official leaderboard
572 CADGenBench submission anonymous_anon-gen-1788549393-ab57_20260904-191634: anon-gen-1788549393-ab57 3.12% version 0.1.0; unvalidated, anonymous Sep 2026 Official leaderboard
573 CADGenBench submission local-user_t051-r010-b2-c_20261102-191249: t051-r010-b2-c 3.10% version 0.1.0; unvalidated, local-user Nov 2026 Official leaderboard
574 CADGenBench submission yitong42_gpt-6-astra-ultra-svg-gpt-5-6-sol-high-c_20260907-173941: GPT-6 Astra Ultra SVG + GPT-5.6-sol high CAD (4-case) 3.09% version 0.1.0; unvalidated, yitong42 Sep 2026 Official leaderboard
575 CADGenBench submission min-liu_chamfer-t2-gen-smoke9_20260709-013720: chamfer-t2-gen-smoke9 3.06% version 0.1.0; unvalidated, Min Liu Jul 2026 Official leaderboard
576 CADGenBench submission pzfreo_opus5-xhigh-mcp-conditional-source-sampl_20260811-160112: opus5-xhigh-mcp-conditional-source-sample6-r1 3.06% version 0.1.0; unvalidated, pzfreo Aug 2026 Official leaderboard
577 CADGenBench submission local-user_t051-r004-c_20261102-022312: t051-r004-c 3.03% version 0.1.0; unvalidated, local-user Nov 2026 Official leaderboard
578 CADGenBench submission local-user_t051-r004-c-infra-retry1_20261102-040853: t051-r004-c-infra-retry1 3.03% version 0.1.0; unvalidated, local-user Nov 2026 Official leaderboard
579 CADGenBench submission min-liu_cad-agent-probe-fusion-360-mcp-x-claude-_20260704-232309: cad-agent probe (Fusion 360 MCP x Claude Opus, fixtures 101-108) 2.98% version 0.1.0; unvalidated, Min Liu Jul 2026 Official leaderboard
580 CADGenBench submission yitong42_svga-g-r2-gpt6-svg-gpt56-cad-840e3511902_20260928-042939: SVGA G-r2 GPT6 SVG GPT56 CAD 840e35119023 2.96% version 0.1.0; unvalidated, yitong42 Sep 2026 Official leaderboard
581 CADGenBench submission cad-mcp-research_inspection-first-comparison-cell-0746582_20260824-054050: inspection-first comparison cell-074658225db50681b737 2.95% version 0.1.0; unvalidated, CAD-MCP Research Aug 2026 Official leaderboard
582 CADGenBench submission anonymous_run-x_20261112-115818: Run X 2.94% version 0.1.0; unvalidated, Anonymous Nov 2026 Official leaderboard
583 CADGenBench submission local-user_t051-r010-b2-b_20261102-194032: t051-r010-b2-b 2.93% version 0.1.0; unvalidated, local-user Nov 2026 Official leaderboard
584 CADGenBench submission local-user_t047-772-fresh-three-a-20261031_20261030-174933: t047-772-fresh-three-a-20261031 2.92% version 0.1.0; unvalidated, local-user Oct 2026 Official leaderboard
585 CADGenBench submission local-user_t051-r005-c_20261102-061259: t051-r005-c 2.90% version 0.1.0; unvalidated, local-user Nov 2026 Official leaderboard
586 CADGenBench submission local-user_t051-r010-b1-c_20261102-184255: t051-r010-b1-c 2.90% version 0.1.0; unvalidated, local-user Nov 2026 Official leaderboard
587 CADGenBench submission yitong42_svgq-a-r1-gpt56-high-618c9855edcd_20260927-191017: SVGQ A-r1 GPT56 high 618c9855edcd 2.88% version 0.1.0; unvalidated, yitong42 Sep 2026 Official leaderboard
588 CADGenBench submission local-user_t051-r010-b1-a_20261102-185031: t051-r010-b1-a 2.86% version 0.1.0; unvalidated, local-user Nov 2026 Official leaderboard
589 CADGenBench submission local-user_t051-r010-b2-a_20261102-192434: t051-r010-b2-a 2.86% version 0.1.0; unvalidated, local-user Nov 2026 Official leaderboard
590 CADGenBench submission anonymous_run-z_20261112-125840: Run Z 2.86% version 0.1.0; unvalidated, Anonymous Nov 2026 Official leaderboard
591 CADGenBench submission cad-mcp-research_inspection-first-comparison-cell-4c0ea99_20260824-055326: inspection-first comparison cell-4c0ea99f1d39970c13cd 2.85% version 0.1.0; unvalidated, CAD-MCP Research Aug 2026 Official leaderboard
592 CADGenBench submission local-user_t047-cvd1-t-20261028_20261028-094744: t047-cvd1-t-20261028 2.83% version 0.1.0; unvalidated, local-user Oct 2026 Official leaderboard
593 CADGenBench submission cad-mcp-research_inspection-first-comparison-cell-630b5e0_20260824-055912: inspection-first comparison cell-630b5e09508b67f40702 2.81% version 0.1.0; unvalidated, CAD-MCP Research Aug 2026 Official leaderboard
594 CADGenBench submission cad-mcp-research_inspection-first-comparison-cell-bb69143_20260824-061044: inspection-first comparison cell-bb691437fd2c19f879ed 2.80% version 0.1.0; unvalidated, CAD-MCP Research Aug 2026 Official leaderboard
595 CADGenBench submission local-user_t051-r010-b1-ab_20261102-190514: t051-r010-b1-ab 2.79% version 0.1.0; unvalidated, local-user Nov 2026 Official leaderboard
596 CADGenBench submission local-user_t047-cvd1-c-20261028_20261028-094122: t047-cvd1-c-20261028 2.77% version 0.1.0; unvalidated, local-user Oct 2026 Official leaderboard
597 CADGenBench submission pzfreo_fable5-v0360-xhigh-smoke3_20260701-221618: fable5-v0360-xhigh-SMOKE3 2.76% version 0.1.0; unvalidated, pzfreo Jul 2026 Official leaderboard
598 CADGenBench submission lehuili_gpt5-6-atomic-reflect-2d_20260909-042736: gpt5.6-atomic-reflect-2D 2.76% version 0.1.0; unvalidated, LehuiLi Sep 2026 Official leaderboard
599 CADGenBench submission cad-mcp-research_inspection-first-development-cell-02cf3d_20260823-002431: inspection-first development cell-02cf3d0c30148c2ed1a1 2.74% version 0.1.0; unvalidated, CAD-MCP Research Aug 2026 Official leaderboard
600 CADGenBench submission yitong42_matched-baseline-codex-gpt-5-6-sol-high-_20260907-092712: Matched baseline + Codex gpt-5.6-sol high (semantic-v1, 4-case) 2.71% version 0.1.0; unvalidated, yitong42 Sep 2026 Official leaderboard
601 CADGenBench submission yitong42_svgq-d-r2-gpt56-high-618c9855edcd_20260927-191631: SVGQ D-r2 GPT56 high 618c9855edcd 2.71% version 0.1.0; unvalidated, yitong42 Sep 2026 Official leaderboard
602 CADGenBench submission anonymous_anon-gen-1787960079-6878_20260828-233440: anon-gen-1787960079-6878 2.66% version 0.1.0; unvalidated, anonymous Aug 2026 Official leaderboard
603 CADGenBench submission anonymous_anon-gen-1787960533-2534_20260828-234214: anon-gen-1787960533-2534 2.66% version 0.1.0; unvalidated, anonymous Aug 2026 Official leaderboard
604 CADGenBench submission cad-mcp-research_inspection-first-development-cell-a60fbd_20260823-014644: inspection-first development cell-a60fbdf6db6c69ed6e10 2.65% version 0.1.0; unvalidated, CAD-MCP Research Aug 2026 Official leaderboard
605 CADGenBench submission yitong42_svgq-c-r1-gpt56-high-618c9855edcd_20260927-191400: SVGQ C-r1 GPT56 high 618c9855edcd 2.63% version 0.1.0; unvalidated, yitong42 Sep 2026 Official leaderboard
606 CADGenBench submission reify_reify-deepseek-low-naked-211-215-config-_20261022-061630: reify-deepseek-low-naked-211-215-config-01 2.62% version 0.1.0; unvalidated, Reify Oct 2026 Official leaderboard
607 CADGenBench submission anon-190312_sweep-d3_20260910-205325: sweep-d3 2.61% version 0.1.0; unvalidated, anon_190312 Sep 2026 Official leaderboard
608 CADGenBench submission local-user_t051-r007-t_20261102-085108: t051-r007-t 2.61% version 0.1.0; unvalidated, local-user Nov 2026 Official leaderboard
609 CADGenBench submission local-user_t051-r006-t_20261102-080915: t051-r006-t 2.60% version 0.1.0; unvalidated, local-user Nov 2026 Official leaderboard
610 CADGenBench submission yitong42_m2d-first-codex-gpt-5-6-sol-high-semanti_20260907-093502: M2D-first + Codex gpt-5.6-sol high (semantic-v1, 4-case) 2.59% version 0.1.0; unvalidated, yitong42 Sep 2026 Official leaderboard
611 CADGenBench submission local-user_t051-r008-t_20261102-094036: t051-r008-t 2.58% version 0.1.0; unvalidated, local-user Nov 2026 Official leaderboard
612 CADGenBench submission yitong42_oldprompt-paired-baseline-gpt-5-6-sol-hi_20260914-152659: OldPrompt paired baseline GPT-5.6-sol high 4-case 20260914-191500 2.57% version 0.1.0; unvalidated, yitong42 Sep 2026 Official leaderboard
613 CADGenBench submission cad-mcp-research_inspection-first-development-cell-0af180_20260823-003654: inspection-first development cell-0af180ba59a5f3524569 2.55% version 0.1.0; unvalidated, CAD-MCP Research Aug 2026 Official leaderboard
614 CADGenBench submission yitong42_metric-m-r1-gpt56-metric-first-svg-cad-e_20260929-090822: METRIC M-r1 GPT56 metric-first SVG CAD ef73db60fade 2.55% version 0.1.0; unvalidated, yitong42 Sep 2026 Official leaderboard
615 CADGenBench submission cad-mcp-research_inspection-first-development-cell-141a78_20260823-004305: inspection-first development cell-141a781f828c31cd9c2a 2.53% version 0.1.0; unvalidated, CAD-MCP Research Aug 2026 Official leaderboard
616 CADGenBench submission yitong42_oldprompt-paired-svg-first-gpt-5-6-sol-h_20260914-152659: OldPrompt paired svg-first GPT-5.6-sol high 4-case 20260914-191500 2.53% version 0.1.0; unvalidated, yitong42 Sep 2026 Official leaderboard
617 CADGenBench submission pzfreo_gpt55-v0364-xhigh-unstepped-retest_20260704-065437: gpt55-v0364-xhigh-unstepped-retest 2.52% version 0.1.0; unvalidated, pzfreo Jul 2026 Official leaderboard
618 CADGenBench submission local-user_t051-r010-b2-ab_20261102-194913: t051-r010-b2-ab 2.52% version 0.1.0; unvalidated, local-user Nov 2026 Official leaderboard
619 CADGenBench submission cad-mcp-research_inspection-first-development-cell-89a36d_20260823-013213: inspection-first development cell-89a36dbcaa2ca924fba8 2.51% version 0.1.0; unvalidated, CAD-MCP Research Aug 2026 Official leaderboard
620 CADGenBench submission yitong42_svgq-b-r1-gpt56-high-618c9855edcd_20260927-191216: SVGQ B-r1 GPT56 high 618c9855edcd 2.51% version 0.1.0; unvalidated, yitong42 Sep 2026 Official leaderboard
621 CADGenBench submission cad-mcp-research_inspection-first-development-cell-76a8b5_20260823-011808: inspection-first development cell-76a8b51ed947e4d1e963 2.50% version 0.1.0; unvalidated, CAD-MCP Research Aug 2026 Official leaderboard
622 CADGenBench submission yitong42_paired-baseline-gpt-5-6-sol-high-4-case-_20260914-100552: Paired baseline GPT-5.6-sol high 4-case 20260914-154500 2.49% version 0.1.0; unvalidated, yitong42 Sep 2026 Official leaderboard
623 CADGenBench submission local-user_t047-0773-feedback-a-20261101_20261101-030942: t047-0773-feedback-a-20261101 2.48% version 0.1.0; unvalidated, local-user Nov 2026 Official leaderboard
624 CADGenBench submission yitong42_svgq-b-r2-gpt56-high-618c9855edcd_20260927-191308: SVGQ B-r2 GPT56 high 618c9855edcd 2.47% version 0.1.0; unvalidated, yitong42 Sep 2026 Official leaderboard
625 CADGenBench submission yitong42_svgq-c-r2-gpt56-high-618c9855edcd_20260927-191451: SVGQ C-r2 GPT56 high 618c9855edcd 2.47% version 0.1.0; unvalidated, yitong42 Sep 2026 Official leaderboard
626 CADGenBench submission pzfreo_gpt55-v0373-smoke5_20260708-102200: gpt55-v0373-smoke5 2.45% version 0.1.0; unvalidated, pzfreo Jul 2026 Official leaderboard
627 CADGenBench submission cad-mcp-research_inspection-first-development-cell-fbc1fc_20260823-015341: inspection-first development cell-fbc1fc0ce6dc251d5efc 2.45% version 0.1.0; unvalidated, CAD-MCP Research Aug 2026 Official leaderboard
628 CADGenBench submission yitong42_paired-svg-first-gpt-5-6-sol-high-4-case_20260914-100759: Paired svg-first GPT-5.6-sol high 4-case 20260914-154500 2.45% version 0.1.0; unvalidated, yitong42 Sep 2026 Official leaderboard
629 CADGenBench submission local-user_gemini38-0773-baseline-20261103-fixturef_20261103-031745: gemini38-0773-baseline-20261103-fixturefix1 2.45% version 0.1.0; unvalidated, local-user Nov 2026 Official leaderboard
630 CADGenBench submission cad-mcp-research_inspection-first-development-cell-067743_20260823-003051: inspection-first development cell-0677434281d885366a2f 2.44% version 0.1.0; unvalidated, CAD-MCP Research Aug 2026 Official leaderboard
631 CADGenBench submission cad-mcp-research_inspection-first-development-cell-fbe5f2_20260823-015910: inspection-first development cell-fbe5f2475be209c783a8 2.43% version 0.1.0; unvalidated, CAD-MCP Research Aug 2026 Official leaderboard
632 CADGenBench submission yitong42_metric-m-r2-gpt56-metric-first-svg-cad-e_20260929-090912: METRIC M-r2 GPT56 metric-first SVG CAD ef73db60fade 2.43% version 0.1.0; unvalidated, yitong42 Sep 2026 Official leaderboard
633 CADGenBench submission niming_a-research_20261002-075325: a_research 2.41% version 0.1.0; unvalidated, niming Oct 2026 Official leaderboard
634 CADGenBench submission local-user_t051-r004-t_20261102-022533: t051-r004-t 2.41% version 0.1.0; unvalidated, local-user Nov 2026 Official leaderboard
635 CADGenBench submission local-user_t051-r004-t-infra-retry1_20261102-041126: t051-r004-t-infra-retry1 2.41% version 0.1.0; unvalidated, local-user Nov 2026 Official leaderboard
636 CADGenBench submission one-research_gpt-5-6-sol-v9-step-r3-101-102-103-128_20260913-135427: GPT-5.6-sol-v9-step-r3-101-102-103-128 2.40% version 0.1.0; unvalidated, one_research Sep 2026 Official leaderboard
637 CADGenBench submission cad-mcp-research_inspection-first-development-cell-6415c0_20260823-010753: inspection-first development cell-6415c0063e381291cecd 2.39% version 0.1.0; unvalidated, CAD-MCP Research Aug 2026 Official leaderboard
638 CADGenBench submission yitong42_direct-svg-first-codex-gpt-5-6-sol-high-_20260907-134035: Direct SVG-first + Codex gpt-5.6-sol high (svg-v2, 4-case) 2.39% version 0.1.0; unvalidated, yitong42 Sep 2026 Official leaderboard
639 CADGenBench submission local-user_t051-r001-d02_20261101-080615: t051-r001-d02 2.39% version 0.1.0; unvalidated, local-user Nov 2026 Official leaderboard
640 CADGenBench submission wolf_pi-agent-4cases-step_20260908-083822: pi-agent-4cases-step 2.38% version 0.1.0; unvalidated, wolf Sep 2026 Official leaderboard
641 CADGenBench submission local-user_t051-r006-c_20261102-080053: t051-r006-c 2.38% version 0.1.0; unvalidated, local-user Nov 2026 Official leaderboard
642 CADGenBench submission yitong42_svgq-a-r2-gpt56-high-618c9855edcd_20260927-191126: SVGQ A-r2 GPT56 high 618c9855edcd 2.36% version 0.1.0; unvalidated, yitong42 Sep 2026 Official leaderboard
643 CADGenBench submission local-user_t047-d1-a-r02-20261027_20261027-162331: t047-d1-a-r02-20261027 2.36% version 0.1.0; unvalidated, local-user Oct 2026 Official leaderboard
644 CADGenBench submission gkgyc233_a-test-of-one-sample-on-gpt-6-astra_20260912-103520: A test of one sample on GPT 6 Astra 2.35% version 0.1.0; unvalidated, Gkgyc233 Sep 2026 Official leaderboard
645 CADGenBench submission local-user_t047-d1-b-r01-20261027_20261027-163207: t047-d1-b-r01-20261027 2.34% version 0.1.0; unvalidated, local-user Oct 2026 Official leaderboard
646 CADGenBench submission local-user_t047-d1-b-r02-20261027_20261027-162745: t047-d1-b-r02-20261027 2.34% version 0.1.0; unvalidated, local-user Oct 2026 Official leaderboard
647 CADGenBench submission cad-mcp-research_inspection-first-development-cell-7eb40f_20260823-012428: inspection-first development cell-7eb40ff4e913fca57016 2.31% version 0.1.0; unvalidated, CAD-MCP Research Aug 2026 Official leaderboard
648 CADGenBench submission local-user_t051-r001-c_20261101-080327: t051-r001-c 2.31% version 0.1.0; unvalidated, local-user Nov 2026 Official leaderboard
649 CADGenBench submission local-user_t051-r001-d03_20261101-080656: t051-r001-d03 2.31% version 0.1.0; unvalidated, local-user Nov 2026 Official leaderboard
650 CADGenBench submission yitong42_autonomous-svg-codex-gpt-5-6-sol-high-ca_20260908-062724: Autonomous SVG + Codex GPT-5.6-sol high CAD (4-case) 2.30% version 0.1.0; unvalidated, yitong42 Sep 2026 Official leaderboard
651 CADGenBench submission marzipan_marzipan_20260910-003143: marzipan 2.29% version 0.1.0; unvalidated, marzipan Sep 2026 Official leaderboard
652 CADGenBench submission w1ne_kernelcad-probe-gen-20261019_20261019-184630: kernelcad-probe-gen-20261019 2.27% version 0.1.0; unvalidated, w1ne Oct 2026 Official leaderboard
653 CADGenBench submission cad-mcp-research_inspection-first-development-cell-00372f_20260823-001706: inspection-first development cell-00372fd9856d4285f61b 2.26% version 0.1.0; unvalidated, CAD-MCP Research Aug 2026 Official leaderboard
654 CADGenBench submission yitong42_svgq-d-r1-gpt56-high-618c9855edcd_20260927-191541: SVGQ D-r1 GPT56 high 618c9855edcd 2.26% version 0.1.0; unvalidated, yitong42 Sep 2026 Official leaderboard
655 CADGenBench submission cad-mcp-research_inspection-first-development-cell-94b7ca_20260823-014156: inspection-first development cell-94b7ca74fcea622f3cac 2.22% version 0.1.0; unvalidated, CAD-MCP Research Aug 2026 Official leaderboard
656 CADGenBench submission arisa_gpt-5-6-sol-step-wise-strategy-v1-r2-101_20260914-114547: GPT-5.6-sol-step-wise-strategy-v1-r2-101-102-103-128 2.21% version 0.1.0; unvalidated, arisa Sep 2026 Official leaderboard
657 CADGenBench submission local-user_t051-r001-d01_20261101-080528: t051-r001-d01 2.20% version 0.1.0; unvalidated, local-user Nov 2026 Official leaderboard
658 CADGenBench submission cad-mcp-research_inspection-first-development-cell-1e4c04_20260823-005013: inspection-first development cell-1e4c046ffffb40877352 2.19% version 0.1.0; unvalidated, CAD-MCP Research Aug 2026 Official leaderboard
659 CADGenBench submission cad-mcp-research_inspection-first-development-cell-357d7d_20260823-005637: inspection-first development cell-357d7d06dcbee1ede716 2.19% version 0.1.0; unvalidated, CAD-MCP Research Aug 2026 Official leaderboard
660 CADGenBench submission local-user_t047-772-feedback-repair-two-20261030_20261030-160122: t047-772-feedback-repair-two-20261030 2.19% version 0.1.0; unvalidated, local-user Oct 2026 Official leaderboard
661 CADGenBench submission local-user_t047-0773-feedback-b-20261101_20261101-034711: t047-0773-feedback-b-20261101 2.17% version 0.1.0; unvalidated, local-user Nov 2026 Official leaderboard
662 CADGenBench submission anonymous_anon-gen-1787959342-3f06_20260828-232223: anon-gen-1787959342-3f06 2.16% version 0.1.0; unvalidated, anonymous Aug 2026 Official leaderboard
663 CADGenBench submission yitong42_m2d-first-codex-gpt-5-6-sol-high-4-case-_20260906-070144: M2D-first + Codex gpt-5.6-sol high (4-case, 20260906) 2.16% version 0.1.0; unvalidated, yitong42 Sep 2026 Official leaderboard
664 CADGenBench submission local-user_t051-r009-t_20261102-131444: t051-r009-t 2.15% version 0.1.0; unvalidated, local-user Nov 2026 Official leaderboard
665 CADGenBench submission local-user_t051-r007-c_20261102-084233: t051-r007-c 2.14% version 0.1.0; unvalidated, local-user Nov 2026 Official leaderboard
666 CADGenBench submission lehuili_gpt-5-6-sol-self-reflect-2d-inspect-4-ca_20260822-071528: GPT-5.6 Sol Self Reflect + 2D Inspect (4-case) 2.13% version 0.1.0; unvalidated, LehuiLi Aug 2026 Official leaderboard
667 CADGenBench submission cad-edit_edit-5-sample-run_20261011-125812: edit-5-sample-run 2.13% version 0.1.0; unvalidated, CAD edit Oct 2026 Official leaderboard
668 CADGenBench submission local-user_t051-r005-t_20261102-063046: t051-r005-t 2.13% version 0.1.0; unvalidated, local-user Nov 2026 Official leaderboard
669 CADGenBench submission local-user_t051-r009-c_20261102-130716: t051-r009-c 2.13% version 0.1.0; unvalidated, local-user Nov 2026 Official leaderboard
670 CADGenBench submission anonymous_ac_20261112-154838: AC 2.11% version 0.1.0; unvalidated, Anonymous Nov 2026 Official leaderboard
671 CADGenBench submission anonymous_ac_20261112-160639: AC 2.11% version 0.1.0; unvalidated, Anonymous Nov 2026 Official leaderboard
672 CADGenBench submission cad-mcp-research_inspection-first-comparison-cell-90ac68c_20260824-060431: inspection-first comparison cell-90ac68cb965dd8f90995 2.06% version 0.1.0; unvalidated, CAD-MCP Research Aug 2026 Official leaderboard
673 CADGenBench submission local-user_t047-tool021-diag-t-r1-20261029_20261029-024855: t047-tool021-diag-t-r1-20261029 2.04% version 0.1.0; unvalidated, local-user Oct 2026 Official leaderboard
674 CADGenBench submission lehuili_gpt-5-6-sol-self-reflect-second-pass-4-c_20260821-152311: GPT-5.6 Sol Self Reflect Second Pass (4-case) 2.03% version 0.1.0; unvalidated, LehuiLi Aug 2026 Official leaderboard
675 CADGenBench submission arisa_gpt-5-6-sol-step-wise-strategy-v1-r1-101_20260914-114510: GPT-5.6-sol-step-wise-strategy-v1-r1-101-102-103-128 2.03% version 0.1.0; unvalidated, arisa Sep 2026 Official leaderboard
676 CADGenBench submission local-user_t047-tool021-diag-c-r1-20261029_20261029-024716: t047-tool021-diag-c-r1-20261029 2.02% version 0.1.0; unvalidated, local-user Oct 2026 Official leaderboard
677 CADGenBench submission local-user_t047-772-fresh-three-b-20261031_20261030-175017: t047-772-fresh-three-b-20261031 2.02% version 0.1.0; unvalidated, local-user Oct 2026 Official leaderboard
678 CADGenBench submission lehuili_gpt-5-6-sol-self-reflect-2d-inspect-same_20260822-083539: GPT-5.6 Sol Self Reflect + 2D Inspect Same-Region Closure (4-case) 2.01% version 0.1.0; unvalidated, LehuiLi Aug 2026 Official leaderboard
679 CADGenBench submission lehuili_gpt-5-6-sol-two-stage-reflection-post-ed_20260822-092931: GPT-5.6 Sol Two-Stage Reflection + Post-Edit Acceptance Closed Loop (4-case) 2.00% version 0.1.0; unvalidated, LehuiLi Aug 2026 Official leaderboard
680 CADGenBench submission wolf_pi-agent-4cases_20260908-083746: pi-agent-4cases 2.00% version 0.1.0; unvalidated, wolf Sep 2026 Official leaderboard
681 CADGenBench submission arisa_gpt-5-6-sol-step-wise-strategy-v1-r3-101_20260914-114625: GPT-5.6-sol-step-wise-strategy-v1-r3-101-102-103-128 1.99% version 0.1.0; unvalidated, arisa Sep 2026 Official leaderboard
682 CADGenBench submission cad-edit-test_test-5-samples_20261011-103623: test-5-samples 1.99% version 0.1.0; unvalidated, CAD-edit-test Oct 2026 Official leaderboard
683 CADGenBench submission lehuili_gpt-5-6-sol-main-agent-self-reflect-4-ca_20260821-122617: GPT-5.6 Sol Main Agent Self Reflect (4-case) 1.98% version 0.1.0; unvalidated, LehuiLi Aug 2026 Official leaderboard
684 CADGenBench submission cad-mcp-research_inspection-first-development-cell-5019c5_20260823-010251: inspection-first development cell-5019c5b12d6b90ed5ca4 1.97% version 0.1.0; unvalidated, CAD-MCP Research Aug 2026 Official leaderboard
685 CADGenBench submission anonymous_anon-gen-1787964075-a10f_20260829-004116: anon-gen-1787964075-a10f 1.97% version 0.1.0; unvalidated, anonymous Aug 2026 Official leaderboard
686 CADGenBench submission anonymous_anon-gen-1787968204-52a0_20260829-015005: anon-gen-1787968204-52a0 1.97% version 0.1.0; unvalidated, anonymous Aug 2026 Official leaderboard
687 CADGenBench submission yitong42_matched-baseline-codex-gpt-5-6-sol-high-_20260906-112731: Matched baseline + Codex gpt-5.6-sol high (4-case) 1.97% version 0.1.0; unvalidated, yitong42 Sep 2026 Official leaderboard
688 CADGenBench submission one-research_gpt-5-6-sol-v9-pi-agent-r3-101-102-103-1_20260913-135330: GPT-5.6-sol-v9-pi-agent-r3-101-102-103-128 1.95% version 0.1.0; unvalidated, one_research Sep 2026 Official leaderboard
689 CADGenBench submission cad-mcp-research_inspection-first-comparison-cell-4519f7a_20260824-054754: inspection-first comparison cell-4519f7a9003e08c7496f 1.94% version 0.1.0; unvalidated, CAD-MCP Research Aug 2026 Official leaderboard
690 CADGenBench submission one-research_gpt-5-6-sol-no-steps_20260910-113355: GPT-5.6-sol-no_steps 1.94% version 0.1.0; unvalidated, one_research Sep 2026 Official leaderboard
691 CADGenBench submission pzfreo_opus5-xhigh-direct-build123d-nomcp-pilot_20260809-174214: opus5-xhigh-direct-build123d-nomcp-pilot2-partial 1.93% version 0.1.0; unvalidated, pzfreo Aug 2026 Official leaderboard
692 CADGenBench submission anonymous_anon-gen-1788135167-b8ef_20260831-001249: anon-gen-1788135167-b8ef 1.93% version 0.1.0; unvalidated, anonymous Aug 2026 Official leaderboard
693 CADGenBench submission one-research_gpt-5-6-sol-steps-rerun_20260910-145136: GPT-5.6-sol-steps-rerun 1.93% version 0.1.0; unvalidated, one_research Sep 2026 Official leaderboard
694 CADGenBench submission lehuili_gpt-5-6-sol-view-search-dual-roi-reflect_20260821-122637: GPT-5.6 Sol View Search + Dual-ROI Reflection (4-case) 1.92% version 0.1.0; unvalidated, LehuiLi Aug 2026 Official leaderboard
695 CADGenBench submission cad-mcp-research_inspection-first-development-cell-6a3b89_20260823-011256: inspection-first development cell-6a3b898bb8fa83f8fb18 1.92% version 0.1.0; unvalidated, CAD-MCP Research Aug 2026 Official leaderboard
696 CADGenBench submission one-research_gpt-5-6-sol-steps_20260910-113415: GPT-5.6-sol-steps 1.92% version 0.1.0; unvalidated, one_research Sep 2026 Official leaderboard
697 CADGenBench submission pzfreo_gpt55-v0372-smoke5_20260707-195934: gpt55-v0372-smoke5 1.91% version 0.1.0; unvalidated, pzfreo Jul 2026 Official leaderboard
698 CADGenBench submission pzfreo_gpt55-v0372-smoke5-r2_20260707-203158: gpt55-v0372-smoke5-r2 1.91% version 0.1.0; unvalidated, pzfreo Jul 2026 Official leaderboard
699 CADGenBench submission one-research_gpt-5-6-sol-v9-pi-agent-r1-101-102-103-1_20260913-134652: GPT-5.6-sol-v9-pi-agent-r1-101-102-103-128 1.90% version 0.1.0; unvalidated, one_research Sep 2026 Official leaderboard
700 CADGenBench submission lehuili_gpt-5-6-sol-self-reflect-two-stage-refle_20260821-155434: GPT-5.6 Sol Self Reflect + Two-Stage Reflection (4-case) 1.87% version 0.1.0; unvalidated, LehuiLi Aug 2026 Official leaderboard
701 CADGenBench submission lehuili_gpt-5-6-sol-view-search-no-crop-reflecti_20260821-122543: GPT-5.6 Sol View Search + No-Crop Reflection (4-case) 1.87% version 0.1.0; unvalidated, LehuiLi Aug 2026 Official leaderboard
702 CADGenBench submission one-research_gpt-5-6-sol-v9-step-r1-101-102-103-128_20260913-135351: GPT-5.6-sol-v9-step-r1-101-102-103-128 1.86% version 0.1.0; unvalidated, one_research Sep 2026 Official leaderboard
703 CADGenBench submission local-user_t047-m1x1-t-20261028_20261028-054234: t047-m1x1-t-20261028 1.85% version 0.1.0; unvalidated, local-user Oct 2026 Official leaderboard
704 CADGenBench submission yitong42_svg-first-codex-gpt-5-6-sol-high-4-case-_20260905-102720: SVG-first Codex + gpt-5.6-sol high (4-case diagnostic) 1.84% version 0.1.0; unvalidated, yitong42 Sep 2026 Official leaderboard
705 CADGenBench submission lehuili_gpt-5-6-sol-main-agent-direct-4-case_20260821-122554: GPT-5.6 Sol Main Agent Direct (4-case) 1.83% version 0.1.0; unvalidated, LehuiLi Aug 2026 Official leaderboard
706 CADGenBench submission lehuili_gpt-5-6-sol-main-agent-fixed-view-2d-sel_20260821-162630: GPT-5.6 Sol Main Agent Fixed-View 2D Self-Reflection (4-case) 1.81% version 0.1.0; unvalidated, LehuiLi Aug 2026 Official leaderboard
707 CADGenBench submission lehuili_gpt-5-6-sol-atomic-geometry-repair-4-cas_20260908-162606: GPT-5.6 Sol Atomic Geometry Repair (4-case, 2026-09-08) 1.80% version 0.1.0; unvalidated, LehuiLi Sep 2026 Official leaderboard
708 CADGenBench submission one-research_gpt-5-6-sol-v9-pi-agent-r2-101-102-103-1_20260913-135255: GPT-5.6-sol-v9-pi-agent-r2-101-102-103-128 1.79% version 0.1.0; unvalidated, one_research Sep 2026 Official leaderboard
709 CADGenBench submission local-user_t047-r3-p2-r02-20261027_20261027-082405: t047-r3-p2-r02-20261027 1.78% version 0.1.0; unvalidated, local-user Oct 2026 Official leaderboard
710 CADGenBench submission anonymous_cadgenbench-111-148-test-2_20260905-132001: CADGenBench 111+148 test 2 1.77% version 0.1.0; unvalidated, Anonymous Sep 2026 Official leaderboard
711 CADGenBench submission one-research_gpt-5-6-sol-no-steps-rerun_20260910-145542: GPT-5.6-sol-no_steps-rerun 1.77% version 0.1.0; unvalidated, one_research Sep 2026 Official leaderboard
712 CADGenBench submission local-user_t047-r3-b-r03-20261027_20261027-082224: t047-r3-b-r03-20261027 1.74% version 0.1.0; unvalidated, local-user Oct 2026 Official leaderboard
713 CADGenBench submission local-user_t051-r010-b1-b_20261102-185656: t051-r010-b1-b 1.74% version 0.1.0; unvalidated, local-user Nov 2026 Official leaderboard
714 CADGenBench submission anonymous_h45-a1-partial_20261021-111114: H45-A1 (partial) 1.72% version 0.1.0; unvalidated, Anonymous Oct 2026 Official leaderboard
715 CADGenBench submission local-user_t047-r3-b-r02-20261027_20261027-082132: t047-r3-b-r02-20261027 1.72% version 0.1.0; unvalidated, local-user Oct 2026 Official leaderboard
716 CADGenBench submission numafi-7095_gen2-numafi-7095_20261102-203546: gen2-numafi-7095 1.72% version 0.1.0; unvalidated, numafi-7095 Nov 2026 Official leaderboard
717 CADGenBench submission local-user_t047-tool021-diag-t-r2-20261029_20261029-025013: t047-tool021-diag-t-r2-20261029 1.71% version 0.1.0; unvalidated, local-user Oct 2026 Official leaderboard
718 CADGenBench submission local-user_t047-r3-p2-r03-20261027_20261027-082506: t047-r3-p2-r03-20261027 1.70% version 0.1.0; unvalidated, local-user Oct 2026 Official leaderboard
719 CADGenBench submission local-user_t051-r008-c_20261102-092933: t051-r008-c 1.70% version 0.1.0; unvalidated, local-user Nov 2026 Official leaderboard
720 CADGenBench submission one-research_gpt-5-6-sol-v9-step-r2-101-102-103-128_20260913-135407: GPT-5.6-sol-v9-step-r2-101-102-103-128 1.69% version 0.1.0; unvalidated, one_research Sep 2026 Official leaderboard
721 CADGenBench submission lehuili_gpt-5-6-sol-main-edit-preview-4-case-202_20260909-030433: GPT-5.6 Sol Main Edit Preview (4-case, 2026-09-09) 1.68% version 0.1.0; unvalidated, LehuiLi Sep 2026 Official leaderboard
722 CADGenBench submission local-user_t047-m1x1-c-20261028_20261028-054131: t047-m1x1-c-20261028 1.68% version 0.1.0; unvalidated, local-user Oct 2026 Official leaderboard
723 CADGenBench submission cad-mcp-research_inspection-first-development-cell-8b3b68_20260823-013718: inspection-first development cell-8b3b6875fd8deb1620d0 1.66% version 0.1.0; unvalidated, CAD-MCP Research Aug 2026 Official leaderboard
724 CADGenBench submission cadgenbench-reflection-study_pi-kimi-k3-reflection-after-102-103-145_20260815-104735: Pi Kimi K3 Reflection AFTER 102 103 145 1.65% version 0.1.0; unvalidated, CADGenBench Reflection Study Aug 2026 Official leaderboard
725 CADGenBench submission cadgenbench-reflection-study_pi-kimi-k3-incremental-editable-reflecti_20260816-202605: Pi Kimi K3 Incremental Editable Reflection Guided 102 103 145 1.63% version 0.1.0; unvalidated, CADGenBench Reflection Study Aug 2026 Official leaderboard
726 CADGenBench submission local-user_t047-d1-a-r01-20261027_20261027-162140: t047-d1-a-r01-20261027 1.62% version 0.1.0; unvalidated, local-user Oct 2026 Official leaderboard
727 CADGenBench submission cadgenbench-reflection-study_pi-kimi-k3-post-submit-dual-roi-reflecti_20260817-033318: Pi Kimi K3 Post-Submit Dual ROI Reflection Guided 102 103 145 1.61% version 0.1.0; unvalidated, CADGenBench Reflection Study Aug 2026 Official leaderboard
728 CADGenBench submission lehuili_gpt-5-6-sol-optional-reflect-causal-repa_20260822-145641: GPT-5.6 Sol Optional Reflect + Causal Repair (4-case) 1.60% version 0.1.0; unvalidated, LehuiLi Aug 2026 Official leaderboard
729 CADGenBench submission local-user_t047-d2g-d3e-c-r01-20261028_20261028-014901: t047-d2g-d3e-c-r01-20261028 1.60% version 0.1.0; unvalidated, local-user Oct 2026 Official leaderboard
730 CADGenBench submission local-user_t047-d2g-d3e-c-r02-20261028_20261028-015028: t047-d2g-d3e-c-r02-20261028 1.60% version 0.1.0; unvalidated, local-user Oct 2026 Official leaderboard
731 CADGenBench submission local-user_t047-d2g-d3e-t-r01-20261028_20261028-015139: t047-d2g-d3e-t-r01-20261028 1.60% version 0.1.0; unvalidated, local-user Oct 2026 Official leaderboard
732 CADGenBench submission local-user_t047-d2g-d3e-t-r02-20261028_20261028-015222: t047-d2g-d3e-t-r02-20261028 1.60% version 0.1.0; unvalidated, local-user Oct 2026 Official leaderboard
733 CADGenBench submission cadgenbench-reflection-study_pi-kimi-k3-dual-roi-reflection-guided-10_20260816-151158: Pi Kimi K3 Dual ROI Reflection Guided 102 103 145 1.59% version 0.1.0; unvalidated, CADGenBench Reflection Study Aug 2026 Official leaderboard
734 CADGenBench submission anonymous_anon-gen-1788070413-8f87_20260830-061334: anon-gen-1788070413-8f87 1.56% version 0.1.0; unvalidated, anonymous Aug 2026 Official leaderboard
735 CADGenBench submission lindacyffan_pi-agent-qwen3-8-steps-101-103-118_20260906-144933: Pi Agent - Qwen3.8-steps- 101+103+118 1.54% version 0.1.0; unvalidated, lindacyffan Sep 2026 Official leaderboard
736 CADGenBench submission cadgenbench-reflection-study_pi-kimi-k3-verified-dual-roi-reflection-_20260816-175950: Pi Kimi K3 Verified Dual ROI Reflection Guided 102 103 145 1.53% version 0.1.0; unvalidated, CADGenBench Reflection Study Aug 2026 Official leaderboard
737 CADGenBench submission anonymous_anon-edit-1787967797-0357_20260829-014318: anon-edit-1787967797-0357 1.53% version 0.1.0; unvalidated, anonymous Aug 2026 Official leaderboard
738 CADGenBench submission paramancer_paramancer-build123d-mcp-0-3-85-dev0-gpt_20261017-123044: paramancer-build123d-mcp-0.3.85.dev0-gpt-6.1-sol-high-pilot-20261017 1.52% version 0.1.0; unvalidated, Paramancer Oct 2026 Official leaderboard
739 CADGenBench submission yitong42_codex-gpt-5-6-sol-high-4-case-baseline_20260905-104105: Codex + gpt-5.6-sol high (4-case baseline) 1.47% version 0.1.0; unvalidated, yitong42 Sep 2026 Official leaderboard
740 CADGenBench submission cadgenbench-reflection-study_pi-kimi-k3-reflection-before-102-103-145_20260815-104640: Pi Kimi K3 Reflection BEFORE 102 103 145 1.44% version 0.1.0; unvalidated, CADGenBench Reflection Study Aug 2026 Official leaderboard
741 CADGenBench submission cadgenbench-reflection-study_pi-kimi-k3-optional-dual-roi-reflection-_20260816-143854: Pi Kimi K3 Optional Dual ROI Reflection 102 103 145 1.44% version 0.1.0; unvalidated, CADGenBench Reflection Study Aug 2026 Official leaderboard
742 CADGenBench submission reify_reify-gpt-6-1-sol-low-101-201-pilot_20261021-080035: Reify GPT-6.1 Sol low - 101 201 pilot 1.42% version 0.1.0; unvalidated, Reify Oct 2026 Official leaderboard
743 CADGenBench submission zky_pi-agent-glm-5-3-flash-fixtures-101-102-_20260902-034512: Pi Agent GLM-5.3-Flash fixtures 101-102-103-111 1.41% version 0.1.0; unvalidated, zky Sep 2026 Official leaderboard
744 CADGenBench submission lindacyffan_pi-agent-qwen3-8-101-103-118_20260906-144715: Pi Agent - Qwen3.8- 101+103+118 1.41% version 0.1.0; unvalidated, lindacyffan Sep 2026 Official leaderboard
745 CADGenBench submission anonymous_anon-edit-1787966903-ab75_20260829-012824: anon-edit-1787966903-ab75 1.38% version 0.1.0; unvalidated, anonymous Aug 2026 Official leaderboard
746 CADGenBench submission reify-evaluation_reify-0-1-1-gpt-5-6-sol-medium-hardest10_20261012-043910: Reify 0.1.1 gpt-5.6-sol medium hardest10 partial3 20261011 1.37% version 0.1.0; unvalidated, Reify evaluation Oct 2026 Official leaderboard
747 CADGenBench submission cadgenbench-reflection-study_pi-kimi-k3-main-agent-self-reflect-102-1_20260815-142707: Pi Kimi K3 Main Agent Self Reflect 102 103 145 1.36% version 0.1.0; unvalidated, CADGenBench Reflection Study Aug 2026 Official leaderboard
748 CADGenBench submission cadgenbench-reflection-study_pi-kimi-k3-fixed-grid-reflection-guided-_20260816-222358: Pi Kimi K3 Fixed Grid Reflection Guided 102 103 145 1.33% version 0.1.0; unvalidated, CADGenBench Reflection Study Aug 2026 Official leaderboard
749 CADGenBench submission verdigris_verdigris_20260909-221559: verdigris 1.28% version 0.1.0; unvalidated, verdigris Sep 2026 Official leaderboard
750 CADGenBench submission local-user_t047-tool021-diag-c-r2-20261029_20261029-024933: t047-tool021-diag-c-r2-20261029 1.26% version 0.1.0; unvalidated, local-user Oct 2026 Official leaderboard
751 CADGenBench submission zky_pi-agent-steps-qwen3-8-103-118_20260906-044155: Pi Agent + steps - Qwen3.8-103 + 118 1.22% version 0.1.0; unvalidated, zky Sep 2026 Official leaderboard
752 CADGenBench submission arisa_gpt-5-6-sol-step-wise-strategy-v1-increm_20260915-053748: GPT-5.6-sol-step-wise-strategy-v1-incremental-visual-check-r1-102-103 1.22% version 0.1.0; unvalidated, arisa Sep 2026 Official leaderboard
753 CADGenBench submission gkgyc233_a-test-of-one-sample-on-gpt-6-astra_20260907-113058: A test of one sample on GPT 6 Astra 1.21% version 0.1.0; unvalidated, Gkgyc233 Sep 2026 Official leaderboard
754 CADGenBench submission anonymous_anon-edit-1788298205-22f6_20260901-213006: anon-edit-1788298205-22f6 1.20% version 0.1.0; unvalidated, anonymous Sep 2026 Official leaderboard
755 CADGenBench submission anonymous_anon-gen-1788803033-562e4d_20260907-174354: anon-gen-1788803033-562e4d 1.20% version 0.1.0; unvalidated, anonymous Sep 2026 Official leaderboard
756 CADGenBench submission lindacyffan_pi-agent-qwen3-8-115-128_20260907-045804: Pi Agent - Qwen3.8-115+128 1.20% version 0.1.0; unvalidated, lindacyffan Sep 2026 Official leaderboard
757 CADGenBench submission anonymous_anon-gen-1789083011-74e9e3_20260911-010046: anon-gen-1789083011-74e9e3 1.20% version 0.1.0; unvalidated, anonymous Sep 2026 Official leaderboard
758 CADGenBench submission reify-evaluation_reify-user-rerun-hardest10-203-20261012_20261012-045422: Reify user rerun hardest10 203 20261012 1.20% version 0.1.0; unvalidated, Reify evaluation Oct 2026 Official leaderboard
759 CADGenBench submission wolf_cadgenresearchs-102-103_20260907-110054: CADgenResearchs-102+103 1.19% version 0.1.0; unvalidated, wolf Sep 2026 Official leaderboard
760 CADGenBench submission zky_pi-agent-qwen3-8-103-118_20260906-042924: Pi Agent Qwen3.8-103 + 118 1.18% version 0.1.0; unvalidated, zky Sep 2026 Official leaderboard
761 CADGenBench submission yitong42_pi-agent-gpt-5-6-sol-high-3-sample-diagn_20260808-093153: Pi Agent + gpt-5.6-sol high (3-sample diagnostic) 1.17% version 0.1.0; unvalidated, yitong42 Aug 2026 Official leaderboard
762 CADGenBench submission zky_pi-agent-glm-5-3-flash-fixtures-101-102-_20260902-023005: Pi Agent GLM-5.3-Flash fixtures 101-102-111 1.17% version 0.1.0; unvalidated, zky Sep 2026 Official leaderboard
763 CADGenBench submission yitong42_codex-gpt-6-astra-ultra-baseline-case-10_20260906-160657: Codex GPT-6 Astra Ultra baseline (case 102) 1.17% version 0.1.0; unvalidated, yitong42 Sep 2026 Official leaderboard
764 CADGenBench submission cadse_gemma-4-e4b-local-4b-drawing-api-idioms-_20261112-093017: Gemma-4-E4B (local, 4B): drawing + API idioms + check loop, first valid of three arms per part, 9 random fixtures (seed 20261112) 1.17% version 0.1.0; unvalidated, CADSE Nov 2026 Official leaderboard
765 CADGenBench submission jake-fitzgerald_codex-build123d-first3-validation_20260609-112054: Codex build123d first3 validation 1.16% version 0.1.0; unvalidated, Jake Fitzgerald Jun 2026 Official leaderboard
766 CADGenBench submission zky_pi-agent-qwen3-8-101-103_20260903-115005: Pi Agent Qwen3.8-101+103 1.16% version 0.1.0; unvalidated, zky Sep 2026 Official leaderboard
767 CADGenBench submission arisa_gpt-5-6-sol-visual-check-oneshot-101-ste_20260915-080620: GPT-5.6-sol-visual-check-oneshot-101-step-128-r1 1.15% version 0.1.0; unvalidated, arisa Sep 2026 Official leaderboard
768 CADGenBench submission independent-cad-workflow_blind-fixture-215-end-disc-thickness-1-t_20260815-095040: Blind fixture 215 end disc thickness 1 to 2 run001 1.14% version 0.1.0; unvalidated, Independent CAD Workflow Aug 2026 Official leaderboard
769 CADGenBench submission w1ne_kernelcad-probe-tiny-20261019_20261019-150640: kernelcad-probe-tiny-20261019 1.13% version 0.1.0; unvalidated, w1ne Oct 2026 Official leaderboard
770 CADGenBench submission reify_reify-deepseek-low-naked-215-export-fix-_20261022-091801: reify-deepseek-low-naked-215-export-fix-01 1.13% version 0.1.0; unvalidated, Reify Oct 2026 Official leaderboard
771 CADGenBench submission jake-fitzgerald_codex-cad-skill-first3-validation_20260609-105454: Codex cad skill first3 validation 1.12% version 0.1.0; unvalidated, Jake Fitzgerald Jun 2026 Official leaderboard
772 CADGenBench submission wolf_cadgenresearch-102-103_20260907-105849: CADgenResearch-102+103 1.09% version 0.1.0; unvalidated, wolf Sep 2026 Official leaderboard
773 CADGenBench submission cad-experiment_two-task-cad-experiment-120-241_20260916-005258: Two-task CAD experiment (120, 241) 1.09% version 0.1.0; unvalidated, CAD Experiment Sep 2026 Official leaderboard
774 CADGenBench submission draw2cad_draw2cad-drawing-derived-101-2026-09-13_20260912-155517: draw2cad drawing-derived 101 2026-09-13 1.07% version 0.1.0; unvalidated, draw2cad Sep 2026 Official leaderboard
775 CADGenBench submission yitong42_codex-gpt-5-6-sol-high-3-sample-diagnost_20260808-084612: Codex + gpt-5.6-sol high (3-sample diagnostic) 1.06% version 0.1.0; unvalidated, yitong42 Aug 2026 Official leaderboard
776 CADGenBench submission independent-cad-workflow_blind-fixture-214-edit-run001_20260813-125249: Blind fixture 214 edit run001 1.06% version 0.1.0; unvalidated, Independent CAD Workflow Aug 2026 Official leaderboard
777 CADGenBench submission cad-mcp-research_canonical-frame-v0-3-17-task105-diagnost_20260823-234206: canonical-frame v0.3.17 task105 diagnostic cell-e24ead3d40780c161662 1.06% version 0.1.0; unvalidated, CAD-MCP Research Aug 2026 Official leaderboard
778 CADGenBench submission independent-cad-workflow_blind-fixture-224-edit-run001_20260813-133148: Blind fixture 224 edit run001 1.05% version 0.1.0; unvalidated, Independent CAD Workflow Aug 2026 Official leaderboard
779 CADGenBench submission anonymous_anon-gen-1789073510-472d47_20260910-205208: anon-gen-1789073510-472d47 1.05% version 0.1.0; unvalidated, anonymous Sep 2026 Official leaderboard
780 CADGenBench submission xyz_gpt-5-6-sol-incremental-v1-generic-stage_20260918-062517: GPT-5.6-sol-incremental-v1-generic-stages-v2-high-step-101-102-r1 1.05% version 0.1.0; unvalidated, xyz Sep 2026 Official leaderboard
781 CADGenBench submission lindacyffan_pi-agent-qwen3-8-steps-115-128_20260907-045831: Pi Agent - Qwen3.8-steps-115+128 1.02% version 0.1.0; unvalidated, lindacyffan Sep 2026 Official leaderboard
782 CADGenBench submission mix_20260920-gpt-5-6-sol-mix-step-101-xhigh-_20260920-142607: 20260920-GPT-5.6-sol-mix-step-101-xhigh-102-high-r1 1.00% version 0.1.0; unvalidated, mix Sep 2026 Official leaderboard
783 CADGenBench submission mliu_chamfer-cad-harness-0-1-2-dev2_20260707-071439: chamfer-cad-harness-0.1.2.dev2 0.99% version 0.1.0; unvalidated, mliu Jul 2026 Official leaderboard
784 CADGenBench submission anonymous_anon-gen-1789073510-1ff981_20260910-210109: anon-gen-1789073510-1ff981 0.98% version 0.1.0; unvalidated, anonymous Sep 2026 Official leaderboard
785 CADGenBench submission o-uz_o-uz-chatgpt-build123d-task-109-pilot-v0_20260817-123006: OĞUZ ChatGPT-build123d Task 109 Pilot v0.1 0.96% version 0.1.0; unvalidated, OĞUZ Aug 2026 Official leaderboard
786 CADGenBench submission yitong42_codex-gpt-6-astra-ultra-self-reconstruct_20260906-161753: Codex GPT-6 Astra Ultra self-reconstructed SVG-CAD (case 102) 0.94% version 0.1.0; unvalidated, yitong42 Sep 2026 Official leaderboard
787 CADGenBench submission lindacyffan_pi-agent-qwen3-8-128_20260907-031448: Pi Agent - Qwen3.8-128 0.93% version 0.1.0; unvalidated, lindacyffan Sep 2026 Official leaderboard
788 CADGenBench submission xyz_gpt-5-6-sol-oneshot-visual-check-high-10_20260918-062536: GPT-5.6-sol-oneshot-visual-check-high-101-102-r1 0.92% version 0.1.0; unvalidated, xyz Sep 2026 Official leaderboard
789 CADGenBench submission lindacyffan_cadresearch-128_20260907-091307: CADResearch-128 0.91% version 0.1.0; unvalidated, lindacyffan Sep 2026 Official leaderboard
790 CADGenBench submission high_20260920-gpt-5-6-sol-incremental-v1-gene_20260920-123924: 20260920-GPT-5.6-sol-incremental-v1-generic-stages-v2-high-step-101-r2 0.91% version 0.1.0; unvalidated, high Sep 2026 Official leaderboard
791 CADGenBench submission mliu_chamfer-cad-harness-0-1-2-dev2_20260707-085910: chamfer-cad-harness-0.1.2.dev2 0.90% version 0.1.0; unvalidated, mliu Jul 2026 Official leaderboard
792 CADGenBench submission lindacyffan_cadresearch-steps-128_20260907-091409: CADResearch-steps-128 0.90% version 0.1.0; unvalidated, lindacyffan Sep 2026 Official leaderboard
793 CADGenBench submission anonymous_anon-edit-1788072384-a74e_20260830-064625: anon-edit-1788072384-a74e 0.89% version 0.1.0; unvalidated, anonymous Aug 2026 Official leaderboard
794 CADGenBench submission zky_pi-agent-glm-5-3-flash-fixtures-101-103_20260902-064301: Pi Agent GLM-5.3-Flash fixtures 101-103 0.89% version 0.1.0; unvalidated, zky Sep 2026 Official leaderboard
795 CADGenBench submission xyz_20260920-gpt-5-6-sol-oneshot-visual-chec_20260920-073517: 20260920-GPT-5.6-sol-oneshot-visual-check-xhigh-102-143-r1 0.89% version 0.1.0; unvalidated, xyz Sep 2026 Official leaderboard
796 CADGenBench submission xyz_20260920-gpt-5-6-sol-incremental-v1-gene_20260920-073552: 20260920-GPT-5.6-sol-incremental-v1-generic-stages-v2-xhigh-step-102-143-r1 0.86% version 0.1.0; unvalidated, xyz Sep 2026 Official leaderboard
797 CADGenBench submission lindacyffan_pi-agent-qwen3-8-steps-128_20260907-031554: Pi Agent - Qwen3.8-steps-128 0.85% version 0.1.0; unvalidated, lindacyffan Sep 2026 Official leaderboard
798 CADGenBench submission anonymous_anon-gen-1789083011-300e52_20260911-005533: anon-gen-1789083011-300e52 0.85% version 0.1.0; unvalidated, anonymous Sep 2026 Official leaderboard
799 CADGenBench submission origogk_origogk-diagnostic-149-voxel-1mm_20260925-153940: OrigoGK diagnostic 149 voxel-1mm 0.85% version 0.1.0; unvalidated, OrigoGK Sep 2026 Official leaderboard
800 CADGenBench submission independent-cad-workflow_blind-fixture-211-top-surface-10-run001_20260815-091450: Blind fixture 211 top surface +10 run001 0.84% version 0.1.0; unvalidated, Independent CAD Workflow Aug 2026 Official leaderboard
801 CADGenBench submission cad-mcp-research_axis-grounded-review-v0-3-8-task105-diag_20260823-203421: axis-grounded-review v0.3.8 task105 diagnostic cell-27fc476f16350bcadf75 0.83% version 0.1.0; unvalidated, CAD-MCP Research Aug 2026 Official leaderboard
802 CADGenBench submission local-user_t047-repair-b-103-20261027_20261027-120251: t047-repair-b-103-20261027 0.83% version 0.1.0; unvalidated, local-user Oct 2026 Official leaderboard
803 CADGenBench submission cad-mcp-research_topology-grounded-v0-3-4-diagnostic-cell_20260823-162546: topology-grounded v0.3.4 diagnostic cell-7c368edcabea6bab12ae 0.82% version 0.1.0; unvalidated, CAD-MCP Research Aug 2026 Official leaderboard
804 CADGenBench submission cad-mcp-research_visual-source-review-v0-3-6-task105-diag_20260823-193859: visual-source-review v0.3.6 task105 diagnostic cell-20f0e795affaafcc30b0 0.79% version 0.1.0; unvalidated, CAD-MCP Research Aug 2026 Official leaderboard
805 CADGenBench submission anonymous_anon-edit-1788156537-2756_20260831-060858: anon-edit-1788156537-2756 0.78% version 0.1.0; unvalidated, anonymous Aug 2026 Official leaderboard
806 CADGenBench submission mix_20260920-gpt-5-6-sol-mix-oneshot-101-xhi_20260920-142541: 20260920-GPT-5.6-sol-mix-oneshot-101-xhigh-102-high-r1 0.78% version 0.1.0; unvalidated, mix Sep 2026 Official leaderboard
807 CADGenBench submission cad-mcp-research_stepped-port-semantics-v0-3-16-task105-d_20260823-224210: stepped-port-semantics v0.3.16 task105 diagnostic cell-a2c78183b51bec3444bd 0.77% version 0.1.0; unvalidated, CAD-MCP Research Aug 2026 Official leaderboard
808 CADGenBench submission zky_pi-agent-glm-5-3-flash-fixtures-101-102_20260901-155807: Pi Agent GLM-5.3-Flash fixtures 101-102 0.77% version 0.1.0; unvalidated, zky Sep 2026 Official leaderboard
809 CADGenBench submission cadse_probe-flipx-part-150-of-the-lean-repeat-_20261112-082959: probe flipx: part 150 of the lean repeat turned 180 deg about X, pose test, 1 fixture 0.76% version 0.1.0; unvalidated, CADSE Nov 2026 Official leaderboard
810 CADGenBench submission independent-cad-workflow_blind-fixture-132-run001_20260812-155030: Blind fixture 132 run001 0.75% version 0.1.0; unvalidated, Independent CAD Workflow Aug 2026 Official leaderboard
811 CADGenBench submission cad-mcp-research_visual-source-review-v0-3-6-task105-diag_20260823-194437: visual-source-review v0.3.6 task105 diagnostic cell-397350b933b119cdb308 0.75% version 0.1.0; unvalidated, CAD-MCP Research Aug 2026 Official leaderboard
812 CADGenBench submission cad-mcp-research_topology-grounded-v0-3-4-diagnostic-cell_20260823-161915: topology-grounded v0.3.4 diagnostic cell-241c6c8e2c57645cbc93 0.74% version 0.1.0; unvalidated, CAD-MCP Research Aug 2026 Official leaderboard
813 CADGenBench submission local-user_t047-repair-p2-103-20261027_20261027-120454: t047-repair-p2-103-20261027 0.74% version 0.1.0; unvalidated, local-user Oct 2026 Official leaderboard
814 CADGenBench submission cadse_probe-rotz-part-150-of-the-lean-repeat-t_20261112-083034: probe rotz: part 150 of the lean repeat turned 180 deg about Z, pose test, 1 fixture 0.74% version 0.1.0; unvalidated, CADSE Nov 2026 Official leaderboard
815 CADGenBench submission wolf_cadgenresearchs-103_20260908-023535: CADgenResearchs-103 0.73% version 0.1.0; unvalidated, wolf Sep 2026 Official leaderboard
816 CADGenBench submission cad-mcp-research_constraint-verified-v0-3-3-diagnostic-ce_20260823-143430: constraint-verified v0.3.3 diagnostic cell-b638afa5499f71d46e2b 0.72% version 0.1.0; unvalidated, CAD-MCP Research Aug 2026 Official leaderboard
817 CADGenBench submission cad-mcp-research_constraint-verified-v0-3-3-diagnostic-ce_20260823-144049: constraint-verified v0.3.3 diagnostic cell-1950efc045c9ce03d939 0.72% version 0.1.0; unvalidated, CAD-MCP Research Aug 2026 Official leaderboard
818 CADGenBench submission lindacyffan_pi-agent-qwen3-8-steps-102-143_20260907-020424: Pi Agent - Qwen3.8-steps- 102+143 0.72% version 0.1.0; unvalidated, lindacyffan Sep 2026 Official leaderboard
819 CADGenBench submission cad-mcp-research_axis-grounded-review-v0-3-8-task105-diag_20260823-202617: axis-grounded-review v0.3.8 task105 diagnostic cell-10fb08d05b9706e8922a 0.71% version 0.1.0; unvalidated, CAD-MCP Research Aug 2026 Official leaderboard
820 CADGenBench submission zky_pi-agent-glm-5-3-flash-fixtures-103-free_20260902-104810: Pi Agent GLM-5.3-Flash fixtures 103（free） 0.71% version 0.1.0; unvalidated, zky Sep 2026 Official leaderboard
821 CADGenBench submission zky_pi-agent-glm-5-3-flash-fixtures-103-free_20260902-124125: Pi Agent GLM-5.3-Flash fixtures 103（free-3） 0.71% version 0.1.0; unvalidated, zky Sep 2026 Official leaderboard
822 CADGenBench submission lindacyffan_pi-agent-qwen3-8-102-143_20260907-020249: Pi Agent - Qwen3.8- 102+143 0.71% version 0.1.0; unvalidated, lindacyffan Sep 2026 Official leaderboard
823 CADGenBench submission cadse_probe-d-part-150-of-the-hole-rules-run-w_20261112-084743: probe d: part 150 of the hole-rules run with the rear slope starting later, 1 fixture 0.71% version 0.1.0; unvalidated, CADSE Nov 2026 Official leaderboard
824 CADGenBench submission cadse_probe-a-part-150-of-the-hole-rules-run-w_20261112-084610: probe a: part 150 of the hole-rules run with shorter floor slots, 1 fixture 0.70% version 0.1.0; unvalidated, CADSE Nov 2026 Official leaderboard
825 CADGenBench submission cadse_probe-b-part-150-of-the-hole-rules-run-w_20261112-084704: probe b: part 150 of the hole-rules run with the 15 mm hole from the top face, 1 fixture 0.70% version 0.1.0; unvalidated, CADSE Nov 2026 Official leaderboard
826 CADGenBench submission cad-mcp-research_inspection-first-diagnostic-cell-eefa0cc_20260824-015832: inspection-first diagnostic cell-eefa0cca2d7cf5523cdd 0.68% version 0.1.0; unvalidated, CAD-MCP Research Aug 2026 Official leaderboard
827 CADGenBench submission zky_pi-agent-qwen3-8-103_20260903-122207: Pi Agent Qwen3.8-103 0.68% version 0.1.0; unvalidated, zky Sep 2026 Official leaderboard
828 CADGenBench submission reify_reify-deepseek-v4-1-flash-medium-assiste_20261021-062037: Reify DeepSeek v4.1 Flash medium - assisted 101 201 pilot 0.64% version 0.1.0; unvalidated, Reify Oct 2026 Official leaderboard
829 CADGenBench submission cad-mcp-research_stepped-port-semantics-v0-3-16-task105-d_20260823-225025: stepped-port-semantics v0.3.16 task105 diagnostic cell-cef4882a7ec02ae5312c 0.61% version 0.1.0; unvalidated, CAD-MCP Research Aug 2026 Official leaderboard
830 CADGenBench submission zky_pi-agent-glm-5-3-flash-fixtures-103-1_20260902-103111: Pi Agent GLM-5.3-Flash fixtures 103（1） 0.61% version 0.1.0; unvalidated, zky Sep 2026 Official leaderboard
831 CADGenBench submission abc_gpt-5-6-sol-stage-ablation-baseline-v1-h_20260916-130122: GPT-5.6-sol-stage-ablation-baseline-v1-high-101 0.61% version 0.1.0; unvalidated, abc Sep 2026 Official leaderboard
832 CADGenBench submission reify_reify-deepseek-low-asi-hard-edit-204-241_20261023-154259: reify-deepseek-low-asi-hard-edit-204-241-243-01 0.61% version 0.1.0; unvalidated, Reify Oct 2026 Official leaderboard
833 CADGenBench submission reify_reify-deepseek-low-naked-204-01_20261024-055930: reify-deepseek-low-naked-204-01 0.61% version 0.1.0; unvalidated, Reify Oct 2026 Official leaderboard
834 CADGenBench submission universe_20260920-gpt-5-6-sol-oneshot-visual-chec_20260920-083649: 20260920-GPT-5.6-sol-oneshot-visual-check-xhigh-101-r1 0.60% version 0.1.0; unvalidated, universe Sep 2026 Official leaderboard
835 CADGenBench submission reify_reify-sol-low-naked-asi-201-comparison_20261021-160613: reify-sol-low-naked-asi-201-comparison 0.60% version 0.1.0; unvalidated, Reify Oct 2026 Official leaderboard
836 CADGenBench submission wolf_cadgenresearchs103_20260908-023513: CADgenResearchs103 0.59% version 0.1.0; unvalidated, wolf Sep 2026 Official leaderboard
837 CADGenBench submission niming_a-research_20261001-134447: a_research 0.59% version 0.1.0; unvalidated, niming Oct 2026 Official leaderboard
838 CADGenBench submission abc_gpt-5-6-sol-stage-ablation-reread-v1-hig_20260916-130223: GPT-5.6-sol-stage-ablation-reread-v1-high-101 0.57% version 0.1.0; unvalidated, abc Sep 2026 Official leaderboard
839 CADGenBench submission pzfreo_gpt55-v0377-xhigh-gen3-dominant_20260710-062829: gpt55-v0377-xhigh-gen3-dominant 0.55% version 0.1.0; unvalidated, pzfreo Jul 2026 Official leaderboard
840 CADGenBench submission lehuili_gpt-5-6-visual-findings-no-dual-roi-case_20260822-211640: GPT-5.6 Visual Findings No Dual ROI (Case 103) 0.54% version 0.1.0; unvalidated, LehuiLi Aug 2026 Official leaderboard
841 CADGenBench submission lehuili_gpt-5-6-sol-optional-reflect-code-ablati_20260830-111204: GPT-5.6 Sol Optional Reflect + Code Ablation (Case 103) 0.54% version 0.1.0; unvalidated, LehuiLi Aug 2026 Official leaderboard
842 CADGenBench submission amy_gpt-5-6-sol-incremental-v1-high-step-101_20260916-092831: GPT-5.6-sol-incremental-v1-high-step-101 0.54% version 0.1.0; unvalidated, amy Sep 2026 Official leaderboard
843 CADGenBench submission charif_antigravity-build123d-agent_20260905-204201: Antigravity Build123d Agent 0.53% version 0.1.0; unvalidated, Charif Sep 2026 Official leaderboard
844 CADGenBench submission abc_gpt-5-6-sol-stage-ablation-focus-v1-high_20260916-130201: GPT-5.6-sol-stage-ablation-focus-v1-high-101 0.53% version 0.1.0; unvalidated, abc Sep 2026 Official leaderboard
845 CADGenBench submission zky_pi-agent-glm-5-3-flash-fixtures-103-free_20260903-061910: Pi Agent GLM-5.3-Flash fixtures 103（free-1） 0.52% version 0.1.0; unvalidated, zky Sep 2026 Official leaderboard
846 CADGenBench submission local-user_t046-cgb101-0770-local-v1_20261026-072818: t046-cgb101-0770-local-v1 0.52% version 0.1.0; unvalidated, local-user Oct 2026 Official leaderboard
847 CADGenBench submission pzfreo_gpt55-v0371-xhigh-tricky3-retry_20260707-122755: gpt55-v0371-xhigh-tricky3-retry 0.51% version 0.1.0; unvalidated, pzfreo Jul 2026 Official leaderboard
848 CADGenBench submission lehuili_gpt-5-6-optional-reflect-persistent-visu_20260822-204648: GPT-5.6 Optional Reflect + Persistent Visual Findings + 2D Completion (Case 103) 0.51% version 0.1.0; unvalidated, LehuiLi Aug 2026 Official leaderboard
849 CADGenBench submission lehuili_gpt-5-6-sol-causal-repair-diverse-hypoth_20260822-170015: GPT-5.6 Sol Causal Repair Diverse Hypotheses (Case 103) 0.51% version 0.1.0; unvalidated, LehuiLi Aug 2026 Official leaderboard
850 CADGenBench submission lindacyffan_pi-agent-qwen3-8-steps-115_20260907-064326: Pi Agent - Qwen3.8-steps-115 0.50% version 0.1.0; unvalidated, lindacyffan Sep 2026 Official leaderboard
851 CADGenBench submission anonymous_anon-edi-1789088523-2764d8_20260911-010231: anon-edi-1789088523-2764d8 0.50% version 0.1.0; unvalidated, anonymous Sep 2026 Official leaderboard
852 CADGenBench submission independent-cad-workflow_blind-fixture-247-edit-run001_20260813-120356: Blind fixture 247 edit run001 0.49% version 0.1.0; unvalidated, Independent CAD Workflow Aug 2026 Official leaderboard
853 CADGenBench submission nrocketmann_cad-agent-deep-build-probe-2-of-81-fixtu_20260831-231311: cad-agent Deep Build probe (2 of 81 fixtures) 0.49% version 0.1.0; unvalidated, nrocketmann Aug 2026 Official leaderboard
854 CADGenBench submission pzfreo_build123d-mcp-0-3-85-dev0-opus-5-xhigh_20260904-183253: build123d-mcp-0.3.85.dev0-opus-5-xhigh 0.49% version 0.1.0; unvalidated, pzfreo Sep 2026 Official leaderboard
855 CADGenBench submission arisa_gpt-5-6-sol-step-wise-strategy-v1-increm_20260915-020357: GPT-5.6-sol-step-wise-strategy-v1-incremental-visual-check-r1-101 0.49% version 0.1.0; unvalidated, arisa Sep 2026 Official leaderboard
856 CADGenBench submission xyz_gpt-5-6-sol-incremental-v1-high-pi-agent_20260917-122313: GPT-5.6-sol-incremental-v1-high-pi-agent-103-r1 0.49% version 0.1.0; unvalidated, xyz Sep 2026 Official leaderboard
857 CADGenBench submission xyz_gpt-5-6-sol-incremental-v1-high-step-103_20260917-122339: GPT-5.6-sol-incremental-v1-high-step-103-r1 0.49% version 0.1.0; unvalidated, xyz Sep 2026 Official leaderboard
858 CADGenBench submission anonymous_anon-edit-1788239926-61c9_20260901-051847: anon-edit-1788239926-61c9 0.47% version 0.1.0; unvalidated, anonymous Sep 2026 Official leaderboard
859 CADGenBench submission high_20260920-gpt-5-6-sol-oneshot-visual-chec_20260920-123853: 20260920-GPT-5.6-sol-oneshot-visual-check-high-101-r2 0.47% version 0.1.0; unvalidated, high Sep 2026 Official leaderboard
860 CADGenBench submission charif_antigravity-build123d_20260903-141338: Antigravity Build123d 0.45% version 0.1.0; unvalidated, Charif Sep 2026 Official leaderboard
861 CADGenBench submission anonymous_anon-edi-1789073510-b03ffd_20260910-210642: anon-edi-1789073510-b03ffd 0.45% version 0.1.0; unvalidated, anonymous Sep 2026 Official leaderboard
862 CADGenBench submission abc_gpt-5-6-sol-stage-ablation-visual-loop-v_20260916-130238: GPT-5.6-sol-stage-ablation-visual-loop-v1-high-101 0.45% version 0.1.0; unvalidated, abc Sep 2026 Official leaderboard
863 CADGenBench submission universe_20260920-gpt-5-6-sol-incremental-v1-gene_20260920-083614: 20260920-GPT-5.6-sol-incremental-v1-generic-stages-v2-xhigh-step-101-r1 0.45% version 0.1.0; unvalidated, universe Sep 2026 Official leaderboard
864 CADGenBench submission cadgenbench-2d-to-3d_dxf-to-fusion-0-6-6-2-track-b-subset-150_20261012-142153: dxf-to-fusion 0.6.6.2 Track B subset (150/129/120) 0.45% version 0.1.0; unvalidated, cadgenbench-2d-to-3d Oct 2026 Official leaderboard
865 CADGenBench submission version5_101-no-step-1_20260909-072608: 101-no_step-1 0.44% version 0.1.0; unvalidated, version5 Sep 2026 Official leaderboard
866 CADGenBench submission anonymous_anon-edit-1788135725-f790_20260831-002206: anon-edit-1788135725-f790 0.42% version 0.1.0; unvalidated, anonymous Aug 2026 Official leaderboard
867 CADGenBench submission anonymous_anon-gen-1788292278-d51a_20260901-195119: anon-gen-1788292278-d51a 0.42% version 0.1.0; unvalidated, anonymous Sep 2026 Official leaderboard
868 CADGenBench submission version5_101-step-2_20260909-072653: 101-_step-2 0.42% version 0.1.0; unvalidated, version5 Sep 2026 Official leaderboard
869 CADGenBench submission zky_pi-agent-glm-5-3-flash-fixtures-103_20260902-093620: Pi Agent GLM-5.3-Flash fixtures 103 0.41% version 0.1.0; unvalidated, zky Sep 2026 Official leaderboard
870 CADGenBench submission wolf_101_20260908-050030: 101 0.41% version 0.1.0; unvalidated, wolf Sep 2026 Official leaderboard
871 CADGenBench submission zky_pi-agent-glm-5-3-flash-fixture-101_20260901-152620: Pi Agent GLM-5.3-Flash fixture 101 0.40% version 0.1.0; unvalidated, zky Sep 2026 Official leaderboard
872 CADGenBench submission zky_pi-agent-qwen3-8-101_20260906-081914: Pi Agent - Qwen3.8-101 0.39% version 0.1.0; unvalidated, zky Sep 2026 Official leaderboard
873 CADGenBench submission zky_pi-agent-steps-qwen3-8-101_20260906-081610: Pi Agent + steps - Qwen3.8-101 0.39% version 0.1.0; unvalidated, zky Sep 2026 Official leaderboard
874 CADGenBench submission wolf_101-step_20260908-055041: 101+step 0.39% version 0.1.0; unvalidated, wolf Sep 2026 Official leaderboard
875 CADGenBench submission amy_gpt-5-6-sol-incremental-v1-high-pi-agent_20260916-092808: GPT-5.6-sol-incremental-v1-high-pi-agent-101 0.39% version 0.1.0; unvalidated, amy Sep 2026 Official leaderboard
876 CADGenBench submission wolf_101-step_20260908-050131: 101-step 0.38% version 0.1.0; unvalidated, wolf Sep 2026 Official leaderboard
877 CADGenBench submission version5_101-no-step-2_20260909-072631: 101-no_step-2 0.38% version 0.1.0; unvalidated, version5 Sep 2026 Official leaderboard
878 CADGenBench submission version5_101-step-1_20260909-072729: 101-_step-1 0.38% version 0.1.0; unvalidated, version5 Sep 2026 Official leaderboard
879 CADGenBench submission independent-cad-workflow_blind-fixture-147-run001_20260812-143651: Blind fixture 147 run001 0.37% version 0.1.0; unvalidated, Independent CAD Workflow Aug 2026 Official leaderboard
880 CADGenBench submission cad-mcp-research_inspection-first-diagnostic-cell-1dd2bf1_20260824-025803: inspection-first diagnostic cell-1dd2bf12c6601f0c9768 0.37% version 0.1.0; unvalidated, CAD-MCP Research Aug 2026 Official leaderboard
881 CADGenBench submission anonymous_cadgenbench-111-148-test_20260905-130419: CADGenBench 111+148 test 0.37% version 0.1.0; unvalidated, Anonymous Sep 2026 Official leaderboard
882 CADGenBench submission zky_pi-agent-qwen3-8-101_20260906-084559: Pi Agent - Qwen3.8- 101 0.37% version 0.1.0; unvalidated, zky Sep 2026 Official leaderboard
883 CADGenBench submission zky_pi-agent-steps-qwen3-8-101_20260906-081537: Pi Agent + steps - Qwen3.8-101 0.37% version 0.1.0; unvalidated, zky Sep 2026 Official leaderboard
884 CADGenBench submission abc_gpt-5-6-sol-incremental-v1-high-step-101_20260917-050510: GPT-5.6-sol-incremental-v1-high-step-101-r2 0.37% version 0.1.0; unvalidated, abc Sep 2026 Official leaderboard
885 CADGenBench submission independent-cad-workflow_blind-fixture-105-generation-run001_20260820-133942: Blind fixture 105 generation run001 0.36% version 0.1.0; unvalidated, Independent CAD Workflow Aug 2026 Official leaderboard
886 CADGenBench submission cad-mcp-research_inspection-first-diagnostic-cell-87cfd25_20260824-025121: inspection-first diagnostic cell-87cfd25994da8be2ca7b 0.35% version 0.1.0; unvalidated, CAD-MCP Research Aug 2026 Official leaderboard
887 CADGenBench submission anonymous_anon-gen-1788239802-e5be_20260901-051643: anon-gen-1788239802-e5be 0.35% version 0.1.0; unvalidated, anonymous Sep 2026 Official leaderboard
888 CADGenBench submission anonymous_anon-gen-1788315559-f1d3_20260902-021920: anon-gen-1788315559-f1d3 0.35% version 0.1.0; unvalidated, anonymous Sep 2026 Official leaderboard
889 CADGenBench submission anonymous_anon-gen-1788372413-975c_20260902-180654: anon-gen-1788372413-975c 0.35% version 0.1.0; unvalidated, anonymous Sep 2026 Official leaderboard
890 CADGenBench submission anonymous_anon-gen-1788372526-ef78_20260902-180848: anon-gen-1788372526-ef78 0.35% version 0.1.0; unvalidated, anonymous Sep 2026 Official leaderboard
891 CADGenBench submission cad-mcp-research_canonical-frame-v0-3-17-task105-diagnost_20260823-231225: canonical-frame v0.3.17 task105 diagnostic cell-129aea4b2a0da94083a2 0.34% version 0.1.0; unvalidated, CAD-MCP Research Aug 2026 Official leaderboard
892 CADGenBench submission abc_gpt-5-6-sol-incremental-v1-high-pi-agent_20260917-055601: GPT-5.6-sol-incremental-v1-high-pi-agent-101-r2 0.34% version 0.1.0; unvalidated, abc Sep 2026 Official leaderboard
893 CADGenBench submission cad-mcp-research_inspection-first-diagnostic-cell-522bc3d_20260824-035018: inspection-first diagnostic cell-522bc3d7f43296e096fa 0.33% version 0.1.0; unvalidated, CAD-MCP Research Aug 2026 Official leaderboard
894 CADGenBench submission cad-mcp-research_baseline-protected-v0-7-9-diagnostic-cel_20260824-151012: baseline-protected v0.7.9 diagnostic cell-de8b1f53d7d7f7d8bd2d 0.32% version 0.1.0; unvalidated, CAD-MCP Research Aug 2026 Official leaderboard
895 CADGenBench submission reify_reify-deepseek-v4-1-flash-low-asi-201-pi_20261021-131436: reify-deepseek-v4-1-flash-low-asi-201-pilot 0.32% version 0.1.0; unvalidated, Reify Oct 2026 Official leaderboard
896 CADGenBench submission anonymous_anon-r1_20260914-093726: anon-r1 0.31% version 0.1.0; unvalidated, anonymous Sep 2026 Official leaderboard
897 CADGenBench submission independent-cad-workflow_blind-fixture-135-run001_20260812-110543: Blind fixture 135 run001 0.30% version 0.1.0; unvalidated, Independent CAD Workflow Aug 2026 Official leaderboard
898 CADGenBench submission cad-mcp-research_baseline-protected-v0-7-9-diagnostic-cel_20260824-152358: baseline-protected v0.7.9 diagnostic cell-3b76b44215889537685b 0.30% version 0.1.0; unvalidated, CAD-MCP Research Aug 2026 Official leaderboard
899 CADGenBench submission cad-mcp-research_inspection-first-diagnostic-cell-390e124_20260824-040229: inspection-first diagnostic cell-390e1241465919b85df2 0.30% version 0.1.0; unvalidated, CAD-MCP Research Aug 2026 Official leaderboard
900 CADGenBench submission lindacyffan_pi-agent-qwen3-8-115_20260907-064412: Pi Agent - Qwen3.8-115 0.30% version 0.1.0; unvalidated, lindacyffan Sep 2026 Official leaderboard
901 CADGenBench submission cad-mcp-research_visual-source-review-v0-3-6-task108-diag_20260823-192923: visual-source-review v0.3.6 task108 diagnostic cell-e4ee681e0ee6afde0895 0.29% version 0.1.0; unvalidated, CAD-MCP Research Aug 2026 Official leaderboard
902 CADGenBench submission cad-mcp-research_canonical-frame-v0-3-17-task112-diagnost_20260824-002039: canonical-frame v0.3.17 task112 diagnostic cell-e83020eae58980dc6d1b 0.28% version 0.1.0; unvalidated, CAD-MCP Research Aug 2026 Official leaderboard
903 CADGenBench submission cad-mcp-research_inspection-first-diagnostic-cell-309f7a3_20260824-030425: inspection-first diagnostic cell-309f7a37fc4fda81d9c4 0.28% version 0.1.0; unvalidated, CAD-MCP Research Aug 2026 Official leaderboard
904 CADGenBench submission wolf_101-pi-agent_20260908-054958: 101+pi-agent 0.27% version 0.1.0; unvalidated, wolf Sep 2026 Official leaderboard
905 CADGenBench submission cad-mcp-research_inspection-first-diagnostic-cell-9c5dd79_20260824-031058: inspection-first diagnostic cell-9c5dd797047d13334d3f 0.26% version 0.1.0; unvalidated, CAD-MCP Research Aug 2026 Official leaderboard
906 CADGenBench submission cad-mcp-research_topology-grounded-v0-3-4-task108-diagnos_20260823-170624: topology-grounded v0.3.4 task108 diagnostic cell-110a7bc4f6be74849f52 0.24% version 0.1.0; unvalidated, CAD-MCP Research Aug 2026 Official leaderboard
907 CADGenBench submission cad-mcp-research_canonical-frame-v0-3-17-task112-diagnost_20260824-001136: canonical-frame v0.3.17 task112 diagnostic cell-e7ff97b17c58e72daddb 0.24% version 0.1.0; unvalidated, CAD-MCP Research Aug 2026 Official leaderboard
908 CADGenBench submission cad-mcp-research_source-reinspection-v0-3-5-task108-diagn_20260823-180206: source-reinspection v0.3.5 task108 diagnostic cell-a1bdca8fc9a8516db2df 0.23% version 0.1.0; unvalidated, CAD-MCP Research Aug 2026 Official leaderboard
909 CADGenBench submission cad-mcp-research_visual-source-review-v0-3-6-task108-diag_20260823-185916: visual-source-review v0.3.6 task108 diagnostic cell-7a3944ae3ceafbce8064 0.23% version 0.1.0; unvalidated, CAD-MCP Research Aug 2026 Official leaderboard
910 CADGenBench submission cad-mcp-research_inspection-first-diagnostic-cell-72c16d1_20260824-031720: inspection-first diagnostic cell-72c16d112fb989a8fe48 0.23% version 0.1.0; unvalidated, CAD-MCP Research Aug 2026 Official leaderboard
911 CADGenBench submission michaelr27_pipeline-smoke-test-box_20260627-135608: Pipeline smoke test (box) 0.19% version 0.1.0; unvalidated, michaelr27 Jun 2026 Official leaderboard
912 CADGenBench submission cad-mcp-research_canonical-frame-v0-3-17-task108-diagnost_20260823-235239: canonical-frame v0.3.17 task108 diagnostic cell-538fe6617610d443d89f 0.18% version 0.1.0; unvalidated, CAD-MCP Research Aug 2026 Official leaderboard
913 CADGenBench submission cad-mcp-research_source-reinspection-v0-3-5-task108-diagn_20260823-175319: source-reinspection v0.3.5 task108 diagnostic cell-847743c3b96ae944b081 0.16% version 0.1.0; unvalidated, CAD-MCP Research Aug 2026 Official leaderboard
914 CADGenBench submission draw2cad_draw2cad-wiring-smoke-2026-09-06_20260906-141211: draw2cad wiring smoke 2026-09-06 0.15% version 0.1.0; unvalidated, draw2cad Sep 2026 Official leaderboard
915 CADGenBench submission cad-mcp-research_topology-grounded-v0-3-4-task108-diagnos_20260823-170052: topology-grounded v0.3.4 task108 diagnostic cell-98e3f7952ceed293cf36 0.14% version 0.1.0; unvalidated, CAD-MCP Research Aug 2026 Official leaderboard
916 CADGenBench submission local-test_fake-mesh-upload-smoke-test_20260612-063710: Fake mesh upload smoke test 0.11% version 0.1.0; unvalidated, Local Test Jun 2026 Official leaderboard
917 CADGenBench submission reify_reify-sol-low-naked-201-comparison_20261021-160213: reify-sol-low-naked-201-comparison 0.08% version 0.1.0; unvalidated, Reify Oct 2026 Official leaderboard
918 CADGenBench submission cad-mcp-research_canonical-frame-v0-3-17-task108-diagnost_20260823-235844: canonical-frame v0.3.17 task108 diagnostic cell-84cac741adb0ef74a571 0% version 0.1.0; unvalidated, CAD-MCP Research Aug 2026 Official leaderboard
#ModelScoreSettingDateSource
1 Claude Fable 5 45.1% HF baseline (Build123d) Jun 2026 Official leaderboard
2 Grok 4.7 44.4% Sep 2026 Lab model card
3 Grok 4.6 40.9% Aug 2026 Lab model card
4 GPT-5.5 Pro 38.7% HF baseline (Build123d) Apr 2026 Official leaderboard
5 Claude Opus 4.7 36.9% HF baseline (Build123d) Apr 2026 Official leaderboard
6 GPT-5.5 36% HF baseline (Build123d) Apr 2026 Official leaderboard
7 Claude Opus 4.8 34.5% HF baseline (Build123d) May 2026 Official leaderboard
8 Gemini 3.1 Pro 31.1% HF baseline (Build123d) Feb 2026 Official leaderboard
9 Claude Opus 4.6 30.9% HF baseline (Build123d) Feb 2026 Official leaderboard
10 Claude Sonnet 4.6 28.3% HF baseline (Build123d) Feb 2026 Official leaderboard
11 Gemini 3.1 Flash-Lite 24.9% HF baseline (Build123d) Mar 2026 Official leaderboard
12 GLM-4.6V 18.3% HF baseline (Build123d) Dec 2025 Official leaderboard
13 Qwen3-VL-235B-A22B-Instruct 16.8% HF baseline (Build123d) Sep 2025 Official leaderboard

Labs report scores for 2 models in their cards. Switch the scores above to rank them together.

2 models have held number one on the official leaderboard since its release in May 2026 2 models have held number one with claims included since its release in May 2026

Lab claims count from the day the card came out, independent runs from the model’s release.

OpenAI Anthropic
Own leaderboard Not tested since Jun 2026
Claude Fable 5 45.1%

Source: Official CADGenBench leaderboard

Scores over time

All the scores we have, one dot each, so a model tested at several settings appears more than once.

On the benchmark’s own leaderboard Reported by the lab in its model card Best so far
0% 20% 40% 60% 80% 100% 2026 Near the ceiling (85%) Claude Fable 5 GPT-5.5 Pro Gemini 3.1 Pro GLM-4.6V 0% 20% 40% 60% 80% 100% 2026 Near the ceiling (85%) Claude Fable 5 GPT-5.5 Pro

Sources: Official CADGenBench leaderboard and labs’ model cards

Labs report it only in system cards

We read the headline results of 522 launch posts from 52 labs, and none of them list this benchmark. Some system cards do, below.

2 system cards report it, from 1 lab

Besides launch posts, we read the system cards, model cards and technical reports labs publish with a release. They report far more, including safety and frontier-risk tests.

DateDocumentScoreAs the document writes itSection
Sep 21, 2026 Grok 4.7 model card 44.4 CADGenBench generation split, reward, high, run by Mecado (4.2) Capabilities
Aug 12, 2026 Grok 4.6 model card 40.9 CADGenBench generation split, reward, high, run by Mecado (4.4) Capabilities

More in Engineering and CAD

All 23 in Engineering and CAD
  • EEBench In use 13 electrical-engineering circuit and PCB design tasks graded by deterministic build checks, simulation and BOM constraints. No LLM judge. Gemini 4 Carbon 83.9%
  • Parametric CAD Bench In use Agents author editable parametric FreeCAD part designs, graded against held-back references for geometry and spec consistency. Claude Opus 5.5 61%
  • 3DCodeBench In use Agentic procedural 3D modeling via code: author engine-ready 3D assets through software APIs. Graded for executability and shape fidelity. LongCat-2.5 55.4%
  • PartBench Only in system cards Parametric mechanical part design and CAD-style generation, graded for geometric and manufacturing fidelity. Grok 4.6 58.5%
  • LMBuild Not in model cards Language model agents design 3D structures as parts, joints, materials and assembly steps. Scoring checks that the structures can be built and work as intended. GPT-6 Astra 66.5%
  • Physical-Engineering's Last Exam Not in model cards Agents produce billable engineering deliverables such as calculation packages, drawings and design reviews in 85 tasks across electrical, civil, structural and mechanical engineering. Automatic graders check constraints, safety limits and the design objective. Claude Opus 5.5 0.49