CADClamp 0.2
Version 0.2
Models generate mechanical parts in seven CAD languages. Each part must meet its specification before the grader compares its printability with a reference part.
The maker ranks 12 models on 47 prompts per language. The ten prompts designated as held out are public.
- Made by
- Christian Hill
- Released
- September 2026
- Kind
- CAD models
- Level
- University
- Scored
- Checked automatically
- Answers
- Code
- Tasks
- All public
- Measures
- Capability
- Subject
- Mechanical engineering
- Language
- English
- Interaction
- Single turn
- Refresh
- New versions replace it
- Run by
- Anyone
- Based on
- CADClamp 0.1
- In views
- CAD
- Strongest model tested
- GPT-6 Astra #4 on the capability index
- Last model added
- September 2026
- Scores refreshed
- November 20th, 2026
Claude Opus 5.5 leads with 0.93 among models released by September 2026
Best score per model from the benchmark's own leaderboard, read on November 20th, 2026. Where a model ran with several settings or harnesses, we keep its best.
The newest model with a score here came out in September 2026, and nobody has tested a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:
- GPT-6.2 Astra
- Claude Fable 5.2
-
Gemini 4 Carbon
- GPT-6.1 Sol
- and 11 more
- 1 Claude Opus 5.5 0.93
- 2 Claude Fable 5.1 0.92
- 3 GPT-6 Astra 0.91
- 4 GPT-6 Sol 0.86
- 5 Grok 4.6 0.83
- 6 Grok 4.7 0.83
- 7 GPT-6 Luna pro 0.77
- 8 Kimi K3 0.75
- 9 Claude Opus 5 0.74
- 10 GPT-5.1 0.20
- 11
Qwen2.5-Coder (7B) 0.01
Source: Official CADClamp 0.2 leaderboard
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Claude Opus 5.5 | 0.93 | Sep 2026 | Official leaderboard | |
| 2 | Claude Fable 5.1 | 0.92 | Sep 2026 | Official leaderboard | |
| 3 | GPT-6 Astra | 0.91 | Sep 2026 | Official leaderboard | |
| 4 | GPT-6 Sol | 0.86 | openrouter | Sep 2026 | Official leaderboard |
| 5 | Grok 4.6 | 0.83 | openrouter | Aug 2026 | Official leaderboard |
| 6 | Grok 4.7 | 0.83 | openrouter | Sep 2026 | Official leaderboard |
| 7 | GPT-6 Luna | 0.77 | pro, openrouter | Sep 2026 | Official leaderboard |
| 8 | Kimi K3 | 0.75 | openrouter | Jul 2026 | Official leaderboard |
| 9 | Claude Opus 5 | 0.74 | claude-cli | Jul 2026 | Official leaderboard |
| 10 | GPT-5.1 | 0.20 | openrouter | Nov 2025 | Official leaderboard |
| 11 | | 0.01 | ollama | Sep 2024 | Official leaderboard |
Rankings by part
We read 9 parts from the benchmark’s own leaderboard, each ranking models on one part of the test, such as build123d, openscad and cadquery. Claude Opus 5.5 leads 4 of them, and 4 other models lead the rest. Arrows show how far a model moved from its overall rank among the models we track.
build123d
11 models we track have a score here.
- 1 GPT-6 Sol ↑3 0.97
- 2 Claude Opus 5.5 ↓1 0.94
- 3 GPT-6 Astra 0.94
- 4 Claude Fable 5.1 ↓2 0.93
- 5 GPT-6 Luna ↑2 0.92
- 6 Grok 4.6 ↓1 0.83
- 7 Claude Opus 5 ↑2 0.80
- 8 Grok 4.7 ↓2 0.79
- 9 Kimi K3 ↓1 0.75
- 10 GPT-5.1 0.04
openscad
11 models we track have a score here.
- 1 Claude Opus 5.5 1.00
- 2 Claude Fable 5.1 0.99
- 3 Grok 4.6 ↑2 0.96
- 4 GPT-6 Astra ↓1 0.94
- 5 GPT-6 Sol ↓1 0.93
- 6 Grok 4.7 0.90
- 7 Kimi K3 ↑1 0.84
- 8 GPT-6 Luna ↓1 0.84
- 9 Claude Opus 5 0.82
- 10 GPT-5.1 0.36
cadquery
11 models we track have a score here.
- 1 GPT-6 Astra ↑2 0.95
- 2 Claude Fable 5.1 0.94
- 3 GPT-6 Sol ↑1 0.93
- 4 Grok 4.7 ↑2 0.92
- 5 GPT-6 Luna ↑2 0.90
- 6 Claude Opus 5.5 ↓5 0.90
- 7 Kimi K3 ↑1 0.86
- 8 Grok 4.6 ↓3 0.82
- 9 Claude Opus 5 0.67
- 10 GPT-5.1 0.21
freecad
11 models we track have a score here.
- 1 Kimi K3 ↑7 0.97
- 2 Claude Opus 5.5 ↓1 0.95
- 3 Claude Fable 5.1 ↓1 0.93
- 4 GPT-6 Sol 0.93
- 5 Grok 4.6 0.92
- 6 GPT-6 Astra ↓3 0.92
- 7 GPT-6 Luna 0.92
- 8 Grok 4.7 ↓2 0.89
- 9 Claude Opus 5 0.88
- 10 GPT-5.1 0.36
rhino
11 models we track have a score here.
- 1 GPT-6 Astra ↑2 0.89
- 2 Claude Opus 5.5 ↓1 0.85
- 3 Claude Fable 5.1 ↓1 0.78
- 4 Grok 4.6 ↑1 0.75
- 5 Grok 4.7 ↑1 0.70
- 6 Claude Opus 5 ↑3 0.68
- 7 Kimi K3 ↑1 0.62
- 8 GPT-6 Sol ↓4 0.60
- 9 GPT-6 Luna ↓2 0.45
- 10 GPT-5.1 0.23
fusion
11 models we track have a score here.
- 1 Claude Fable 5.1 ↑1 0.95
- 2 Claude Opus 5.5 ↓1 0.93
- 3 GPT-6 Astra 0.84
- 4 GPT-6 Sol 0.82
- 5 Grok 4.7 ↑1 0.73
- 6 Grok 4.6 ↓1 0.67
- 7 Claude Opus 5 ↑2 0.54
- 8 GPT-6 Luna ↓1 0.52
- 9 Kimi K3 ↓1 0.37
- 10 GPT-5.1 0.04
blender
11 models we track have a score here.
- 1 Claude Opus 5.5 0.94
- 2 Claude Fable 5.1 0.93
- 3 GPT-6 Astra 0.93
- 4 GPT-6 Luna ↑3 0.90
- 5 Grok 4.6 0.88
- 6 Kimi K3 ↑2 0.86
- 7 GPT-6 Sol ↓3 0.86
- 8 Grok 4.7 ↓2 0.85
- 9 Claude Opus 5 0.79
- 10 GPT-5.1 0.13
Public
11 models we track have a score here.
- 1 Claude Opus 5.5 0.94
- 2 Claude Fable 5.1 0.94
- 3 GPT-6 Astra 0.92
- 4 GPT-6 Sol 0.86
- 5 Grok 4.7 ↑1 0.84
- 6 Grok 4.6 ↓1 0.84
- 7 GPT-6 Luna 0.78
- 8 Kimi K3 0.76
- 9 Claude Opus 5 0.73
- 10 GPT-5.1 0.19
Held out
11 models we track have a score here.
- 1 Claude Opus 5.5 0.90
- 2 GPT-6 Astra ↑1 0.89
- 3 Claude Fable 5.1 ↓1 0.87
- 4 GPT-6 Sol 0.87
- 5 Grok 4.6 0.83
- 6 Grok 4.7 0.80
- 7 Claude Opus 5 ↑2 0.76
- 8 GPT-6 Luna ↓1 0.76
- 9 Kimi K3 ↓1 0.74
- 10 GPT-5.1 0.20
2 models have held number one on the official leaderboard since its release in September 2026
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: Official CADClamp 0.2 leaderboard
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
Source: Official CADClamp 0.2 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
- 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 10 checks pass. Every benchmark
Catalog record 2 pass
- Pass Task access All tasks are public.
- Pass Confidence Checked against a primary source.
Scores 4 pass 1 note
- Pass Independent runs Scores from the official leaderboard (11 entries).
- Pass Models scored 11 models we track.
- Pass Newest score The newest is from September 2026, for Claude Opus 5.5.
- Pass Frontier models 3 of the top 10 have a score, led by GPT-6 Astra (#4).
- Note Headroom Scored as a plain number, with no fixed ceiling.
Leaderboard import 3 pass
- Pass Importer We read the board on christiannhill.github.io: 12 rows for models we track 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.