cad-spec
Models write CadQuery code for mounting plates from dimensioned specifications. The evaluator measures each finished solid against nine requirements.
On November 19, 2026, DeepSeek Chat V3 0324 led 16 models at 78% across four held-out tiers. GPT-4.1 nano scored 63%, and Qwen3 Coder Next scored 61%.
- Made by
- cad-spec team
- Released
- August 2026
- Kind
- CAD models
- Level
- University
- Scored
- Checked automatically
- Answers
- Code
- Tasks
- All public
- Measures
- Capability
- Language
- English
- Interaction
- Single turn
- Refresh
- One fixed set
- Run by
- A host
- In views
- CAD
- Strongest model tested
-
Qwen3-235B-A22B-Instruct Jul 2025 #133 on the capability index
- Last model added
- February 2026
- Scores refreshed
- November 20th, 2026
DeepSeek-V3 leads with 78% among models released by February 2026 DeepSeek-V3 leads with 78% 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:
- GPT-6.2 Astra
- Claude Fable 5.2
-
Gemini 4 Carbon
- GPT-6 Astra
- and 16 more
- 78.0
DeepSeek-V3
- 63.0 GPT-4.1 nano
- 61.0
Qwen3-Coder-Next
- 59.0
Qwen3-235B-A22B-Instruct
- 40.0 GPT-4o mini
- 33.0
Llama 4 Maverick
- 32.0
Mistral Small 3.2
- 28.0
Qwen3-Coder-30B-A3B-Instruct
- 18.0
Phi-4
- 18.0
Qwen3-30B-A3B-Instruct
- 16.0
Llama 3.3 70B Instruct
- 13.0 mistralai/codestral-2508
- 12.0
Gemma 3 27B
- 8.00 meta-llama/llama-3.1-8b-instruct
- 8.00
Gemma 3 4B
- 7.00
Qwen2.5-Coder (1.5B)
- 1
DeepSeek-V3 Mar 2025, greedy 78%
- 2 GPT-4.1 nano greedy 63%
- 3
Qwen3-Coder-Next greedy 61%
- 4
Qwen3-235B-A22B-Instruct Jul 2025, greedy 59%
- 5 GPT-4o mini greedy 40%
- 6
Llama 4 Maverick greedy 33%
- 7
Mistral Small 3.2 greedy 32%
- 8
Qwen3-Coder-30B-A3B-Instruct greedy 28%
- 9
Phi-4 greedy 18%
- 10
Qwen3-30B-A3B-Instruct Jul 2025, greedy 18%
- 11
Llama 3.3 70B Instruct greedy 16%
- 12 mistralai/codestral-2508 greedy 13%
- 13
Gemma 3 27B greedy 12%
- 14 meta-llama/llama-3.1-8b-instruct greedy 8.00%
- 15
Gemma 3 4B greedy 8.00%
- 16
Qwen2.5-Coder (1.5B) greedy 7.00%
Source: Official cad-spec leaderboard
- 78.0
DeepSeek-V3
- 63.0 GPT-4.1 nano
- 61.0
Qwen3-Coder-Next
- 59.0
Qwen3-235B-A22B-Instruct
- 40.0 GPT-4o mini
- 33.0
Llama 4 Maverick
- 32.0
Mistral Small 3.2
- 28.0
Qwen3-Coder-30B-A3B-Instruct
- 18.0
Phi-4
- 18.0
Qwen3-30B-A3B-Instruct
- 16.0
Llama 3.3 70B Instruct
- 12.0
Gemma 3 27B
- 8.00
Gemma 3 4B
- 7.00
Qwen2.5-Coder (1.5B)
- 1
DeepSeek-V3 Mar 2025, greedy 78%
- 2 GPT-4.1 nano greedy 63%
- 3
Qwen3-Coder-Next greedy 61%
- 4
Qwen3-235B-A22B-Instruct Jul 2025, greedy 59%
- 5 GPT-4o mini greedy 40%
- 6
Llama 4 Maverick greedy 33%
- 7
Mistral Small 3.2 greedy 32%
- 8
Qwen3-Coder-30B-A3B-Instruct greedy 28%
- 9
Phi-4 greedy 18%
- 10
Qwen3-30B-A3B-Instruct Jul 2025, greedy 18%
- 11
Llama 3.3 70B Instruct greedy 16%
- 12
Gemma 3 27B greedy 12%
- 13
Gemma 3 4B greedy 8.00%
- 14
Qwen2.5-Coder (1.5B) greedy 7.00%
Source: Official cad-spec leaderboard
| # | Entry | Score ± | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | | 78% 72 to 85 | greedy | Mar 2025 | Official leaderboard |
| 2 | GPT-4.1 nano | 63% 56 to 71 | greedy | Apr 2025 | Official leaderboard |
| 3 | | 61% ±7 | greedy | Feb 2026 | Official leaderboard |
| 4 | | 59% ±8 | greedy | Jul 2025 | Official leaderboard |
| 5 | GPT-4o mini | 40% 33 to 46 | greedy | Jul 2024 | Official leaderboard |
| 6 | | 33% 26 to 41 | greedy | Apr 2025 | Official leaderboard |
| 7 | | 32% 25 to 40 | greedy | Jun 2025 | Official leaderboard |
| 8 | | 28% 22 to 36 | greedy | Jul 2025 | Official leaderboard |
| 9 | | 18% ±5 | greedy | Dec 2024 | Official leaderboard |
| 10 | | 18% ±4 | greedy | Jul 2025 | Official leaderboard |
| 11 | | 16% ±4 | greedy | Dec 2024 | Official leaderboard |
| 12 | mistralai/codestral-2508 | 13% 9 to 18 | greedy | Official leaderboard | |
| 13 | | 12% ±4 | greedy | Mar 2025 | Official leaderboard |
| 14 | meta-llama/llama-3.1-8b-instruct | 8.00% ±4 | greedy | Official leaderboard | |
| 15 | | 8.00% ±4 | greedy | Mar 2025 | Official leaderboard |
| 16 | | 7.00% ±4 | greedy | Sep 2024 | Official leaderboard |
| # | Model | Score ± | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | | 78% 72 to 85 | greedy | Mar 2025 | Official leaderboard |
| 2 | GPT-4.1 nano | 63% 56 to 71 | greedy | Apr 2025 | Official leaderboard |
| 3 | | 61% ±7 | greedy | Feb 2026 | Official leaderboard |
| 4 | | 59% ±8 | greedy | Jul 2025 | Official leaderboard |
| 5 | GPT-4o mini | 40% 33 to 46 | greedy | Jul 2024 | Official leaderboard |
| 6 | | 33% 26 to 41 | greedy | Apr 2025 | Official leaderboard |
| 7 | | 32% 25 to 40 | greedy | Jun 2025 | Official leaderboard |
| 8 | | 28% 22 to 36 | greedy | Jul 2025 | Official leaderboard |
| 9 | | 18% ±5 | greedy | Dec 2024 | Official leaderboard |
| 10 | | 18% ±4 | greedy | Jul 2025 | Official leaderboard |
| 11 | | 16% ±4 | greedy | Dec 2024 | Official leaderboard |
| 12 | | 12% ±4 | greedy | Mar 2025 | Official leaderboard |
| 13 | | 8.00% ±4 | greedy | Mar 2025 | Official leaderboard |
| 14 | | 7.00% ±4 | greedy | Sep 2024 | Official leaderboard |
Rankings by part
We read 5 parts from the benchmark’s own leaderboard, each ranking models on one part of the test, such as L0, L1 and L2. GPT-4o mini leads 1 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.
L0
14 models we track have a score here.
- 1 GPT-4o mini ↑4 100%
- 2
Qwen2.5-Coder (1.5B) ↑12 100%
- 3
Llama 3.3 70B Instruct ↑8 100%
- 4
Gemma 3 27B ↑8 100%
- 5
DeepSeek-V3 Mar 2025 ↓4 100%
- 6
Qwen3-235B-A22B-Instruct Jul 2025 ↓2 100%
- 7
Gemma 3 4B ↑6 97%
- 8 GPT-4.1 nano ↓6 97%
- 9
Qwen3-Coder-Next ↓6 97%
- 10
Phi-4 ↓1 93%
L1
14 models we track have a score here.
- 1
DeepSeek-V3 Mar 2025 97%
- 2
Qwen3-Coder-Next ↑1 77%
- 3
Qwen3-235B-A22B-Instruct Jul 2025 ↑1 67%
- 4 GPT-4.1 nano ↓2 60%
- 5
Mistral Small 3.2 ↑2 47%
- 6
Phi-4 ↑3 37%
- 7
Qwen3-30B-A3B-Instruct Jul 2025 ↑3 10%
- 8
Llama 4 Maverick ↓2 7.00%
- 9
Qwen3-Coder-30B-A3B-Instruct ↓1 7.00%
- 10 GPT-4o mini ↓5 0%
L2
14 models we track have a score here.
- 1 GPT-4.1 nano ↑1 100%
- 2
DeepSeek-V3 Mar 2025 ↓1 93%
- 3
Qwen3-235B-A22B-Instruct Jul 2025 ↑1 83%
- 4
Qwen3-Coder-Next ↓1 83%
- 5 GPT-4o mini 67%
- 6
Qwen3-Coder-30B-A3B-Instruct ↑2 40%
- 7
Mistral Small 3.2 10%
- 8
Llama 4 Maverick ↓2 3.00%
- 9
Qwen2.5-Coder (1.5B) ↑5 0%
- 10
Llama 3.3 70B Instruct ↑1 0%
L3
14 models we track have a score here.
- 1
Llama 4 Maverick ↑5 70%
- 2
DeepSeek-V3 Mar 2025 ↓1 63%
- 3 GPT-4o mini ↑2 60%
- 4 GPT-4.1 nano ↓2 60%
- 5
Qwen3-235B-A22B-Instruct Jul 2025 ↓1 33%
- 6
Qwen3-Coder-Next ↓3 27%
- 7
Mistral Small 3.2 20%
- 8
Qwen3-30B-A3B-Instruct Jul 2025 ↑2 17%
- 9
Qwen3-Coder-30B-A3B-Instruct ↓1 13%
- 10
Qwen2.5-Coder (1.5B) ↑4 0%
L4
14 models we track have a score here.
- 1
Llama 3.3 70B Instruct ↑10 63%
- 2
DeepSeek-V3 Mar 2025 ↓1 60%
- 3
Qwen3-Coder-Next 57%
- 4
Llama 4 Maverick ↑2 53%
- 5
Mistral Small 3.2 ↑2 53%
- 6
Qwen3-235B-A22B-Instruct Jul 2025 ↓2 53%
- 7
Qwen3-Coder-30B-A3B-Instruct ↑1 53%
- 8
Gemma 3 27B ↑4 47%
- 9
Qwen3-30B-A3B-Instruct Jul 2025 ↑1 47%
- 10
Phi-4 ↓1 37%
The best score, 78%, costs $0.03 for the full run
Runs on the cost frontier score higher than any run that's cheaper. The costs are the leaderboard's own estimates, so compare them only within this benchmark.
Source: Official cad-spec leaderboard
| Model | Effort | Harness | Score | Cost of the full run | Output tokens |
|---|---|---|---|---|---|
| greedy | 78% | $0.03 | |||
| GPT-4.1 nano | greedy | 63% | $0.01 | ||
| greedy | 61% | $0.04 | |||
| greedy | 59% | $0.02 | |||
| GPT-4o mini | greedy | 40% | $0.02 | ||
| greedy | 33% | $0.03 | |||
| greedy | 32% | $0.008 | |||
| greedy | 28% | $0.01 | |||
| greedy | 18% | $0.007 | |||
| greedy | 18% | $0.01 | |||
| greedy | 16% | $0.02 | |||
| greedy | 12% | $0.01 | |||
| greedy | 8.00% | $0.005 | |||
| greedy | 7.00% |
The best score, 78%, costs $0.03 for the full run
Runs on the cost frontier score higher than any run that's cheaper. The costs are the leaderboard's own estimates, so compare them only within this benchmark.
Source: Official cad-spec leaderboard
| Model | Effort | Harness | Score | Cost of the full run | Output tokens |
|---|---|---|---|---|---|
| greedy | 78% | $0.03 | |||
| GPT-4.1 nano | greedy | 63% | $0.01 | ||
| greedy | 61% | $0.04 | |||
| greedy | 59% | $0.02 | |||
| GPT-4o mini | greedy | 40% | $0.02 | ||
| greedy | 33% | $0.03 | |||
| greedy | 32% | $0.008 | |||
| greedy | 28% | $0.01 | |||
| greedy | 18% | $0.007 | |||
| greedy | 18% | $0.01 | |||
| greedy | 16% | $0.02 | |||
| greedy | 12% | $0.01 | |||
| greedy | 8.00% | $0.005 | |||
| greedy | 7.00% |
Number one over time
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: Official cad-spec 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 cad-spec 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 9 months ago, in February 2026, for Qwen3-Coder-Next. 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 (16 entries).
- Pass Models scored 14 models we track, plus 2 other entries on its leaderboard.
- Warning Newest score The newest came 9 months ago, in February 2026, for Qwen3-Coder-Next.
- Note Frontier models None of the top 10 has a score. The strongest tested is Qwen3-235B-A22B-Instruct (#133).
- Pass Headroom The best is 78%, under 85%, so it still separates models.
Leaderboard import 3 pass
- Pass Importer We read the board on github.com: 14 rows for models we track and 2 other entries 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.