MUSE (CAD assemblies)
Models turn design specifications into CAD assemblies. A program checks the geometry. A vision model grades function, manufacturability, and ease of assembly.
The authors rank 15 models across 106 design cases. Gemini 3.1 Pro grades the designs, including its own. Failed executions receive zero.
- Made by
- Xiaoyu Dong and colleagues
- Released
- May 2026
- Kind
- CAD models
- Level
- University
- Scored
- Graded by a model
- Answers
- Code
- Tasks
- All public
- Measures
- Capability
- Subject
- Mechanical engineering
- Language
- English
- Interaction
- Single turn
- Refresh
- One fixed set
- Run by
- Anyone
- In views
- CAD
- Strongest model tested
- GPT-5.5 #21 on the capability index
- Last model added
- April 2026
- Scores refreshed
- November 20th, 2026
GPT-5.5 leads with 52.4% among models released by April 2026 GPT-5.5 leads with 52.4% among models released by April 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 April 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 Astra
- and 16 more
- 1 GPT-5.5 52.4%
- 2
Gemini 3.1 Pro 43.4%
- 3 Claude Opus 4.7 39.5%
- 4 GLM-5.1 18.9%
- 5 Claude 3.7 Sonnet 12.7%
- 6
Qwen3.5-122B-A10B 8.33%
- 7
MiniMax-M2.7 5.66%
- 8 GPT-4o Mar 2025 5.03%
- 9
Qwen2.5-72B 4.40%
- 10
Qwen 3.6 35B-A3B 4.09%
- 11 qwen-3.6-coder 3.30%
- 12
MiniMax-M2.5 2.83%
- 13 glm-4.7-flash 2.36%
- 14
Llama 3.1-70B 2.20%
- 15
Llama 3.1-8B 0%
Source: Official MUSE (CAD assemblies) leaderboard
- 1 GPT-5.5 52.4%
- 2
Gemini 3.1 Pro 43.4%
- 3 Claude Opus 4.7 39.5%
- 4 GLM-5.1 18.9%
- 5 Claude 3.7 Sonnet 12.7%
- 6
Qwen3.5-122B-A10B 8.33%
- 7
MiniMax-M2.7 5.66%
- 8 GPT-4o Mar 2025 5.03%
- 9
Qwen2.5-72B 4.40%
- 10
Qwen 3.6 35B-A3B 4.09%
- 11
MiniMax-M2.5 2.83%
- 12 glm-4.7-flash 2.36%
- 13
Llama 3.1-70B 2.20%
- 14
Llama 3.1-8B 0%
Source: Official MUSE (CAD assemblies) leaderboard
| # | Entry | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | GPT-5.5 | 52.4% | Apr 2026 | Official leaderboard | |
| 2 | | 43.4% | Feb 2026 | Official leaderboard | |
| 3 | Claude Opus 4.7 | 39.5% | Apr 2026 | Official leaderboard | |
| 4 | GLM-5.1 | 18.9% | Apr 2026 | Official leaderboard | |
| 5 | Claude 3.7 Sonnet | 12.7% | Feb 2025 | Official leaderboard | |
| 6 | | 8.33% | Feb 2026 | Official leaderboard | |
| 7 | | 5.66% | Mar 2026 | Official leaderboard | |
| 8 | GPT-4o Mar 2025 | 5.03% | Mar 2025 | Official leaderboard | |
| 9 | | 4.40% | Sep 2024 | Official leaderboard | |
| 10 | | 4.09% | Apr 2026 | Official leaderboard | |
| 11 | qwen-3.6-coder open weights | 3.30% | Official leaderboard | ||
| 12 | | 2.83% | Feb 2026 | Official leaderboard | |
| 13 | glm-4.7-flash | 2.36% | Jan 2026 | Official leaderboard | |
| 14 | | 2.20% | Jul 2024 | Official leaderboard | |
| 15 | | 0% | Jul 2024 | Official leaderboard |
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | GPT-5.5 | 52.4% | Apr 2026 | Official leaderboard | |
| 2 | | 43.4% | Feb 2026 | Official leaderboard | |
| 3 | Claude Opus 4.7 | 39.5% | Apr 2026 | Official leaderboard | |
| 4 | GLM-5.1 | 18.9% | Apr 2026 | Official leaderboard | |
| 5 | Claude 3.7 Sonnet | 12.7% | Feb 2025 | Official leaderboard | |
| 6 | | 8.33% | Feb 2026 | Official leaderboard | |
| 7 | | 5.66% | Mar 2026 | Official leaderboard | |
| 8 | GPT-4o Mar 2025 | 5.03% | Mar 2025 | Official leaderboard | |
| 9 | | 4.40% | Sep 2024 | Official leaderboard | |
| 10 | | 4.09% | Apr 2026 | Official leaderboard | |
| 11 | | 2.83% | Feb 2026 | Official leaderboard | |
| 12 | glm-4.7-flash | 2.36% | Jan 2026 | Official leaderboard | |
| 13 | | 2.20% | Jul 2024 | Official leaderboard | |
| 14 | | 0% | Jul 2024 | Official leaderboard |
Rankings by part
We read 3 parts from the benchmark’s own leaderboard: Functionality, Manufacturability and Assemblability. Each ranks models on one part of the test. GPT-5.5 leads every one of them. Arrows show how far a model moved from its overall rank among the models we track.
Functionality
14 models we track have a score here.
- 1 GPT-5.5 54.7%
- 2
Gemini 3.1 Pro 47.6%
- 3 Claude Opus 4.7 42.9%
- 4 GLM-5.1 18.9%
- 5 Claude 3.7 Sonnet 12.3%
- 6
Qwen3.5-122B-A10B 8.49%
- 7
MiniMax-M2.7 5.19%
- 8 GPT-4o Mar 2025 3.77%
- 9
Qwen 3.6 35B-A3B ↑1 3.77%
- 10
Qwen2.5-72B ↓1 2.83%
Manufacturability
14 models we track have a score here.
- 1 GPT-5.5 48.6%
- 2
Gemini 3.1 Pro 41%
- 3 Claude Opus 4.7 36.8%
- 4 GLM-5.1 17.4%
- 5 Claude 3.7 Sonnet 11.8%
- 6
Qwen3.5-122B-A10B 7.55%
- 7
MiniMax-M2.7 5.66%
- 8
Qwen2.5-72B ↑1 4.72%
- 9 GPT-4o Mar 2025 ↓1 4.72%
- 10
Qwen 3.6 35B-A3B 3.77%
Assemblability
14 models we track have a score here.
- 1 GPT-5.5 53.8%
- 2
Gemini 3.1 Pro 41.5%
- 3 Claude Opus 4.7 38.7%
- 4 GLM-5.1 20.3%
- 5 Claude 3.7 Sonnet 14.2%
- 6
Qwen3.5-122B-A10B 8.96%
- 7 GPT-4o Mar 2025 ↑1 6.60%
- 8
MiniMax-M2.7 ↓1 6.13%
- 9
Qwen2.5-72B 5.66%
- 10
Qwen 3.6 35B-A3B 4.72%
Number one over time
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: Official MUSE (CAD assemblies) 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 MUSE (CAD assemblies) 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
- 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 7 months ago, in April 2026, for GPT-5.5. 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 (15 entries).
- Pass Models scored 14 models we track, plus 1 other entry on its leaderboard.
- Warning Newest score The newest came 7 months ago, in April 2026, for GPT-5.5.
- Note Frontier models None of the top 10 has a score. The strongest tested is GPT-5.5 (#21).
- Pass Headroom The best is 52.4%, under 85%, so it still separates models.
Leaderboard import 3 pass
- Pass Importer We read the board on dong7313.github.io: 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.