CadEval leaderboard
As of 6 Nov 2026, the top score on CadEval is 74.0% by o3 (OpenAI), ahead of Gemini 2.5 Pro at 64.0%, across 15 model configurations with a published result (Epoch AI Benchmarking Hub, result dated 16 Apr 2025). The model writes CAD code to produce a part matching a specification, checked geometrically. CadEval is shown for reference only and does not count toward the BenchLeader Index.
Key facts (as of 6 Nov 2026)
- o3 holds the top CadEval score at 74.0% (Epoch AI Benchmarking Hub, 16 Apr 2025).
- Gemini 2.5 Pro is second on CadEval at 64.0% (Epoch AI Benchmarking Hub, 31 Mar 2025).
- CadEval: Generating CAD models from specifications (Epoch AI Benchmarking Hub).
- 15 model configurations have a published CadEval result on BenchLeader (BenchLeader, 6 Nov 2026).
- CadEval does not feed the BenchLeader Index; it is shown for reference (BenchLeader methodology).
Generating CAD models from specifications.
- Published by
- Epoch AI Benchmarking Hub
- Category
- Coding
- Index weight
- Reference only
- Models
- 15
- Data as of
- 6 Nov 2026
CC BY 4.0 — Epoch AI, ‘AI Benchmarking Hub’, epoch.ai/benchmarks. Mirrored boards credit their original publishers.
What the test looks like
The model writes CAD code to produce a part matching a specification, checked geometrically.
How it is scored
Overall pass rate, as published.
What to keep in mind
Small set; a niche but checkable skill.
- 1o3 (medium)74.0%
- 2Gemini 2.5 Pro64.0%
- 3o4-mini (medium)62.0%
- 4o1 (medium)56.0%
- 5Claude 3.7 Sonnet54.0%
- 6o3-mini (medium)54.0%
- 7Claude 3.5 Sonnet48.0%
- 8GPT-4.142.0%
- 9Gemini 1.5 Pro 00234.0%
- 10Claude 3.5 Haiku32.0%
- 11Gemini 2.0 Flash30.0%
- 12GPT-4o26.0%
- 13ml-elephant20.0%
- 14GPT-4.1 mini16.0%
- 15Claude 3 Haiku12.0%
| # | ||||
|---|---|---|---|---|
| 1 |  o3medium | 74.0% | 53.3 | 2025-04-16 |
| 2 |  Gemini 2.5 Pro | 64.0% | 54.5 | 2025-03-31 |
| 3 | o4-minimedium | 62.0% | 51.8 | 2025-04-16 |
| 4 | o1medium | 56.0% | 48.1 | 2024-12-17 |
| 5 |  Claude 3.7 Sonnet | 54.0% | 49.9 | 2025-02-24 |
| 6 | o3-minimedium | 54.0% | 45.2 | 2025-01-31 |
| 7 | Claude 3.5 Sonnet | 48.0% | 47.1 | 2024-10-22 |
| 8 | GPT-4.1 | 42.0% | 48.5 | 2025-04-14 |
| 9 | Gemini 1.5 Pro 002 | 34.0% | 41.5 | 2024-09-24 |
| 10 | Claude 3.5 Haiku | 32.0% | 38.8 | 2024-10-22 |
| 11 | Gemini 2.0 Flash | 30.0% | 43.5 | 2025-02-05 |
| 12 | GPT-4o | 26.0% | 43.3 | 2024-08-06 |
| 13 | ml-elephant | 20.0% | – | – |
| 14 | GPT-4.1 mini | 16.0% | 44.8 | 2025-04-14 |
| 15 | Claude 3 Haiku | 12.0% | 36.3 | 2024-03-07 |
More coding benchmarks · All LLM benchmarks
Related benchmarks
Cite as: BenchLeader, “CadEval leaderboard”, data as of 6 Nov 2026, https://www.benchleader.com/benchmarks/cad_eval.
CadEval: questions
- What does CadEval measure?
- The model writes CAD code to produce a part matching a specification, checked geometrically. Scores are reported in percent of tasks solved; higher is better.
- What is the top score on CadEval?
- As of 6 Nov 2026, the highest score on CadEval is 74.0% by o3 (result dated 16 Apr 2025), ahead of Gemini 2.5 Pro at 64.0%. Scores come from Epoch AI Benchmarking Hub and are re-read daily.
- Which AI model leads CadEval?
- o3 leads CadEval with 74.0% as of 6 Nov 2026 (result dated 16 Apr 2025), ahead of Gemini 2.5 Pro at 64.0%.
- How many models have CadEval results?
- 15 model configurations have a CadEval result on BenchLeader, all taken from Epoch AI Benchmarking Hub.
- Who runs CadEval and how often is it updated?
- CadEval is published by Epoch AI Benchmarking Hub. BenchLeader re-reads the published results once a day and records the date each result was published.
- Does CadEval count toward the BenchLeader Index?
- No. CadEval is shown for reference but left out of the composite index.