Benchmark Almanac

CADTestBench

Claude Sonnet 4.6 81% leads since May 2026
Not in model cards

Models generate mechanical parts from text. Executable tests check the geometry and topology of each solid. A part passes when it satisfies every test.

The authors compare five language model planners on 200 parts, each with an abstract prompt and a detailed prompt. They publish separate scores for each prompt type.

Released
May 2026
Kind
CAD models
Level
University
Scored
Checked automatically
Answers
Code
Tasks
All public
Measures
Capability
Language
English
In and out
Text → Code
Interaction
Single turn
Refresh
One fixed set
Run by
Anyone
In views
CAD
Strongest model tested
GPT-5.2 #51 on the capability index
Last model added
February 2026
Scores refreshed
November 20th, 2026
6
Entries on its own leaderboard, 5 models we track

Claude Sonnet 4.6 leads with 81% among models released by February 2026 Claude Sonnet 4.6 leads with 81% among models released by February 2026

Best score per entry from the benchmark's own leaderboard, read on November 20th, 2026. Where a model ran with several settings or harnesses, we keep its best. Every run is in the next chart. Names in gray aren't in our model list: fine-tunes, agent systems, products and older models. They don't count toward leaders. This view shows only models we track, each at its best.

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

  1. 1 Claude Sonnet 4.6 Abstract 81%
  2. 2 GPT-5.2 Abstract 72%
  3. 3 GPT-4.1 Abstract 63%
  4. 4 Qwen3-Coder-480B-A35B Abstract 60.5%
  5. 5 DeepSeek-V3 Mar 2025, Abstract 39%
  6. 6 Text2CAD Abstract 8.50%

Source: Official CADTestBench leaderboard

#EntryScoreSettingDateSource
1 Claude Sonnet 4.6 81% Abstract, CADTests + Log Feb 2026 Official leaderboard
2 GPT-5.2 72% Abstract, CADTests Dec 2025 Official leaderboard
3 GPT-4.1 63% Abstract, CadCodeVerify Apr 2025 Official leaderboard
4 Qwen3-Coder-480B-A35B 60.5% Abstract, ReAct Jul 2025 Official leaderboard
5 DeepSeek-V3 Mar 2025 39% Abstract, ReAct Mar 2025 Official leaderboard
6 Text2CAD 8.50% Abstract Official leaderboard
#ModelScoreSettingDateSource
1 Claude Sonnet 4.6 81% Abstract, CADTests + Log Feb 2026 Official leaderboard
2 GPT-5.2 72% Abstract, CADTests Dec 2025 Official leaderboard
3 GPT-4.1 63% Abstract, CadCodeVerify Apr 2025 Official leaderboard
4 Qwen3-Coder-480B-A35B 60.5% Abstract, ReAct Jul 2025 Official leaderboard
5 DeepSeek-V3 Mar 2025 39% Abstract, ReAct Mar 2025 Official leaderboard

Scores at each effort level

Models the leaderboard ran at two or more effort levels. We don’t have enough cost data here to say what the extra effort costs.

Lowest effort to highest, light to dark
Claude Sonnet 4.6 CADTests + Log
Detailed Abstract
81%
Claude Sonnet 4.6 CADTests
Detailed Abstract
76.5%
GPT-5.2 CADTests
Detailed Abstract
72%
Claude Sonnet 4.6 ReAct
Detailed Abstract
71.5%
GPT-5.2 CADTests + Log
Detailed Abstract
70%
GPT-5.2 ReAct
Detailed Abstract
69.5%
GPT-5.2 ReAct + Image
Detailed Abstract
69.5%
Claude Sonnet 4.6 10-shots
Detailed Abstract
64%
Claude Sonnet 4.6 Skilled
Detailed Abstract
64%
GPT-4.1 CadCodeVerify
Detailed Abstract
63%
Qwen3-Coder-480B-A35B ReAct
Detailed Abstract
60.5%
GPT-5.2 Skilled
Detailed Abstract
60%

Source: Official CADTestBench leaderboard

ModelEffortHarnessScoreCost per taskOutput tokens
Claude Sonnet 4.6 Abstract CADTests + Log 81%
Claude Sonnet 4.6 Abstract CADTests 76.5%
GPT-5.2 Abstract CADTests 72%
Claude Sonnet 4.6 Abstract ReAct 71.5%
GPT-5.2 Abstract CADTests + Log 70%
GPT-5.2 Abstract ReAct 69.5%
GPT-5.2 Abstract ReAct + Image 69.5%
Claude Sonnet 4.6 Abstract 10-shots 64%
Claude Sonnet 4.6 Abstract Skilled 64%
GPT-4.1 Abstract CadCodeVerify 63%
Claude Sonnet 4.6 Detailed CADTests + Log 62.5%
Qwen3-Coder-480B-A35B Abstract ReAct 60.5%
GPT-5.2 Abstract Skilled 60%
Claude Sonnet 4.6 Detailed CADTests 59%
GPT-5.2 Abstract 10-shots 58%
Claude Sonnet 4.6 Detailed ReAct 58%
GPT-5.2 Detailed CADTests + Log 51.5%
Claude Sonnet 4.6 Detailed 10-shots 51%
Claude Sonnet 4.6 Detailed Skilled 50.5%
GPT-5.2 Detailed CADTests 50%
GPT-5.2 Detailed ReAct + Image 48.5%
GPT-5.2 Detailed ReAct 48%
GPT-5.2 Detailed 10-shots 46.5%
GPT-5.2 Detailed Skilled 43%
Qwen3-Coder-480B-A35B Detailed ReAct 42.5%
GPT-4.1 Detailed CadCodeVerify 41%
DeepSeek-V3 Mar 2025 Abstract ReAct 39%
DeepSeek-V3 Mar 2025 Detailed ReAct 37%

Scores at each effort level

Models the leaderboard ran at two or more effort levels. We don’t have enough cost data here to say what the extra effort costs.

Lowest effort to highest, light to dark
Claude Sonnet 4.6 CADTests + Log
Detailed Abstract
81%
Claude Sonnet 4.6 CADTests
Detailed Abstract
76.5%
GPT-5.2 CADTests
Detailed Abstract
72%
Claude Sonnet 4.6 ReAct
Detailed Abstract
71.5%
GPT-5.2 CADTests + Log
Detailed Abstract
70%
GPT-5.2 ReAct
Detailed Abstract
69.5%
GPT-5.2 ReAct + Image
Detailed Abstract
69.5%
Claude Sonnet 4.6 10-shots
Detailed Abstract
64%
Claude Sonnet 4.6 Skilled
Detailed Abstract
64%
GPT-4.1 CadCodeVerify
Detailed Abstract
63%
Qwen3-Coder-480B-A35B ReAct
Detailed Abstract
60.5%
GPT-5.2 Skilled
Detailed Abstract
60%

Source: Official CADTestBench leaderboard

ModelEffortHarnessScoreCost per taskOutput tokens
Claude Sonnet 4.6 Abstract CADTests + Log 81%
Claude Sonnet 4.6 Abstract CADTests 76.5%
GPT-5.2 Abstract CADTests 72%
Claude Sonnet 4.6 Abstract ReAct 71.5%
GPT-5.2 Abstract CADTests + Log 70%
GPT-5.2 Abstract ReAct 69.5%
GPT-5.2 Abstract ReAct + Image 69.5%
Claude Sonnet 4.6 Abstract 10-shots 64%
Claude Sonnet 4.6 Abstract Skilled 64%
GPT-4.1 Abstract CadCodeVerify 63%
Claude Sonnet 4.6 Detailed CADTests + Log 62.5%
Qwen3-Coder-480B-A35B Abstract ReAct 60.5%
GPT-5.2 Abstract Skilled 60%
Claude Sonnet 4.6 Detailed CADTests 59%
GPT-5.2 Abstract 10-shots 58%
Claude Sonnet 4.6 Detailed ReAct 58%
GPT-5.2 Detailed CADTests + Log 51.5%
Claude Sonnet 4.6 Detailed 10-shots 51%
Claude Sonnet 4.6 Detailed Skilled 50.5%
GPT-5.2 Detailed CADTests 50%
GPT-5.2 Detailed ReAct + Image 48.5%
GPT-5.2 Detailed ReAct 48%
GPT-5.2 Detailed 10-shots 46.5%
GPT-5.2 Detailed Skilled 43%
Qwen3-Coder-480B-A35B Detailed ReAct 42.5%
GPT-4.1 Detailed CadCodeVerify 41%
DeepSeek-V3 Mar 2025 Abstract ReAct 39%
DeepSeek-V3 Mar 2025 Detailed ReAct 37%

Number one over time

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

Anthropic
Own leaderboard Not tested since May 2026

Source: Official CADTestBench leaderboard

Scores over time

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

Plot with other benchmarks
On the benchmark’s own leaderboard Best so far
0% 20% 40% 60% 80% 100% 2025 2026 Near the ceiling (85%) Claude Sonnet 4.6 GPT-5.2 GPT-4.1 DeepSeek-V3 0% 20% 40% 60% 80% 100% 2025 2026 Near the ceiling (85%) Claude Sonnet 4.6 GPT-5.2

Source: Official CADTestBench leaderboard

No lab model card reports it yet

We read the headline results of 540 launch posts from 57 labs, and none of them list this benchmark.

More in Engineering and CAD

All 112 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%
  • 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%
  • CADGenBench Only in system cards Agents construct CAD models from design prompts. The generation split is graded for executability and geometric correctness. Claude Fable 5 45.1%
  • PartBench Only in system cards Parametric mechanical part design and CAD-style generation, graded for geometric and manufacturing fidelity. Grok 4.6 58.5%
  • Razavi-Bench Not in model cards Models explain what happens in analog circuits and why. A language model awards up to four points per answer against a reference and a rubric. Gemini 4 Carbon 98.3%
  • CircuitRubric Not in model cards Models write analog circuit netlists from design requests. A program compares transistor connections and relative device sizes with accepted reference circuits. Claude Opus 4.8 96%

Data audit

9 of 10 checks pass, 1 warning. Look first at the Newest score check. The newest came 9 months ago, in February 2026, for Claude Sonnet 4.6. Every benchmark

Catalog record 2 pass
  • Pass Task access All tasks are public.
  • Pass Confidence Checked against a primary source.
Scores 1 warning 3 pass 1 note
  • Pass Independent runs Scores from the official leaderboard (6 entries).
  • Pass Models scored 5 models we track, plus 1 other entry on its leaderboard.
  • Warning Newest score The newest came 9 months ago, in February 2026, for Claude Sonnet 4.6.
  • Note Frontier models None of the top 10 has a score. The strongest tested is GPT-5.2 (#51).
  • Pass Headroom The best is 81%, under 85%, so it still separates models.
Leaderboard import 3 pass
  • Pass Importer We read the board on dimitrismallis.github.io: 28 rows for models we track and 1 other entry at the last read.
  • Pass Last read November 20th, 2026.
  • Pass Read worked The last read worked.
Consistency 1 pass 1 note
  • Note Lab claims No model has both a lab number and an independent run.
  • Pass Known issues No published audit found problems.

How we check