Benchmark Almanac

CADClamp 0.2

Claude Opus 5.5 0.93 leads since September 2026
Not in model cards
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
Language
English
In and out
Text → Code
Interaction
Single turn
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
11
Models scored on its own leaderboard

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:

  1. 1 Claude Opus 5.5 0.93
  2. 2 Claude Fable 5.1 0.92
  3. 3 GPT-6 Astra 0.91
  4. 4 GPT-6 Sol 0.86
  5. 5 Grok 4.6 0.83
  6. 6 Grok 4.7 0.83
  7. 7 GPT-6 Luna pro 0.77
  8. 8 Kimi K3 0.75
  9. 9 Claude Opus 5 0.74
  10. 10 GPT-5.1 0.20
  11. 11 Qwen2.5-Coder (7B) 0.01

Source: Official CADClamp 0.2 leaderboard

#ModelScoreSettingDateSource
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 Qwen2.5-Coder (7B) 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. 1 GPT-6 Sol ↑3 0.97
  2. 2 Claude Opus 5.5 ↓1 0.94
  3. 3 GPT-6 Astra 0.94
  4. 4 Claude Fable 5.1 ↓2 0.93
  5. 5 GPT-6 Luna ↑2 0.92
  6. 6 Grok 4.6 ↓1 0.83
  7. 7 Claude Opus 5 ↑2 0.80
  8. 8 Grok 4.7 ↓2 0.79
  9. 9 Kimi K3 ↓1 0.75
  10. 10 GPT-5.1 0.04

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.

Anthropic
Own leaderboard Not tested since Sep 2026

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.

Plot with other benchmarks
On the benchmark’s own leaderboard
0.00 0.20 0.40 0.60 0.80 1.00 2025 2026 0.00 0.20 0.40 0.60 0.80 1.00 2025 2026

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

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 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.

How we check