Benchmark Almanac

CADClamp 0.1

Claude Opus 5 0.89 leads since August 2026
Not in model cards
Version 0.1

Models write programs for mechanical parts in OpenSCAD and build123d. The grader checks the resulting solids and scores their suitability for 3D printing.

The maker ranks 15 models on 20 prompts in each language, with three attempts per prompt. This version reports raw printability.

Made by
Christian Hill
Released
August 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
Run by
Anyone
In views
CAD
Strongest model tested
Claude Opus 5 #11 on the capability index
Last model added
August 2026
Scores refreshed
November 20th, 2026
15
Entries on its own leaderboard, 14 models we track

2 models share the top score of 0.89 among models released by August 2026 2 models share the top score of 0.89 among models released by August 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. 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 August 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 Opus 5 0.89
  2. 2 Grok 4.6 0.89
  3. 3 Kimi K3 0.82
  4. 4 Gemini 3.1 Pro 0.82
  5. 5 Claude Sonnet 5 0.82
  6. 6 Kimi K2.7 Code 0.76
  7. 7 DeepSeek-V4-Pro 0.75
  8. 8 Gemini 3.6 Flash 0.74
  9. 9 GLM-5.2 0.66
  10. 10 GPT-5.1-Codex 0.63
  11. 11 MiniMax-M3 0.61
  12. 12 GPT-5.1 0.54
  13. 13 seed-2.0-code 0.52
  14. 14 Qwen3-Coder-Next 0.40
  15. 15 Qwen3-Max 0.38

Source: Official CADClamp 0.1 leaderboard

#EntryScoreSettingDateSource
1 Claude Opus 5 0.89 Jul 2026 Official leaderboard
2 Grok 4.6 0.89 Aug 2026 Official leaderboard
3 Kimi K3 0.82 Jul 2026 Official leaderboard
4 Gemini 3.1 Pro 0.82 Feb 2026 Official leaderboard
5 Claude Sonnet 5 0.82 Jun 2026 Official leaderboard
6 Kimi K2.7 Code 0.76 Jun 2026 Official leaderboard
7 DeepSeek-V4-Pro 0.75 Apr 2026 Official leaderboard
8 Gemini 3.6 Flash 0.74 Jul 2026 Official leaderboard
9 GLM-5.2 0.66 Jun 2026 Official leaderboard
10 GPT-5.1-Codex 0.63 Nov 2025 Official leaderboard
11 MiniMax-M3 0.61 Jun 2026 Official leaderboard
12 GPT-5.1 0.54 Nov 2025 Official leaderboard
13 seed-2.0-code 0.52 Official leaderboard
14 Qwen3-Coder-Next 0.40 Feb 2026 Official leaderboard
15 Qwen3-Max 0.38 Sep 2025 Official leaderboard
#ModelScoreSettingDateSource
1 Claude Opus 5 0.89 Jul 2026 Official leaderboard
2 Grok 4.6 0.89 Aug 2026 Official leaderboard
3 Kimi K3 0.82 Jul 2026 Official leaderboard
4 Gemini 3.1 Pro 0.82 Feb 2026 Official leaderboard
5 Claude Sonnet 5 0.82 Jun 2026 Official leaderboard
6 Kimi K2.7 Code 0.76 Jun 2026 Official leaderboard
7 DeepSeek-V4-Pro 0.75 Apr 2026 Official leaderboard
8 Gemini 3.6 Flash 0.74 Jul 2026 Official leaderboard
9 GLM-5.2 0.66 Jun 2026 Official leaderboard
10 GPT-5.1-Codex 0.63 Nov 2025 Official leaderboard
11 MiniMax-M3 0.61 Jun 2026 Official leaderboard
12 GPT-5.1 0.54 Nov 2025 Official leaderboard
13 Qwen3-Coder-Next 0.40 Feb 2026 Official leaderboard
14 Qwen3-Max 0.38 Sep 2025 Official leaderboard

Rankings by part

We read 2 parts from the benchmark’s own leaderboard: build123d and OpenSCAD. Each ranks models on one part of the test. Claude Opus 5 leads build123d and Grok 4.6 leads OpenSCAD. Arrows show how far a model moved from its overall rank among the models we track.

build123d

14 models we track have a score here.

  1. 1 Claude Opus 5 0.90
  2. 2 Grok 4.6 0.84
  3. 3 Claude Sonnet 5 ↑2 0.82
  4. 4 Kimi K3 ↓1 0.81
  5. 5 Gemini 3.1 Pro ↓1 0.76
  6. 6 Kimi K2.7 Code 0.70
  7. 7 DeepSeek-V4-Pro 0.67
  8. 8 Gemini 3.6 Flash 0.62
  9. 9 MiniMax-M3 ↑2 0.55
  10. 10 Qwen3-Max ↑4 0.50

Number one over time

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

Anthropic
Own leaderboard Replaced by 0.2, Sep 2026

Source: Official CADClamp 0.1 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
0.40 0.60 0.80 1.00 2026 0.40 0.60 0.80 1.00 2026

Source: Official CADClamp 0.1 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.

Versions

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

All 9 checks pass. Every benchmark

Catalog record 2 pass
  • Pass Task access All tasks are public.
  • Pass Confidence Checked against a primary source.
Scores 3 pass 2 notes
  • Pass Independent runs Scores from the official leaderboard (15 entries).
  • Pass Models scored 14 models we track, plus 1 other entry on its leaderboard.
  • Pass Newest score The newest is from August 2026, for Grok 4.6.
  • Note Frontier models None of the top 10 has a score, which is fine for a retired test. The strongest tested is Claude Opus 5 (#11).
  • Note Headroom Scored as a plain number, with no fixed ceiling.
Leaderboard import 3 pass
  • Pass Importer We read the board on github.com: 14 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