Coding benchmark # CadEval leaderboard > CadEval results for 14 AI models, led by o3 at 74%. What the benchmark measures, who runs it, and a source for every score. - Canonical page: https://noometry.com/benchmarks/cadeval - Last updated: 2026-10-10 - Title: CadEval Leaderboard (October 2026): Scores by Model As of October 2026, o3 has the highest published CadEval score on Noometry at 74%, out of 14 models with results. Last verified October 10, 2026 ## About CadEval Generating CAD code for 3D parts from text descriptions. - **Category:** [Coding](https://noometry.com/best/coding) - **Introduced:** 2025 - **Unit:** Percent (random guessing ≈ 0%) - **Official site:** [github.com](https://github.com/wgpatrick/cadeval) ## Top 14 models Top models on CadEval 1. o3 74% 2. Gemini 2.5 Pro 64% 3. o4-mini 62% 4. o1 56% 5. Claude 3.7 Sonnet 54% 6. o3-mini 54% 7. Claude 3.5 Sonnet 48% 8. GPT-4.1 42% 9. Gemini 1.5 Pro (May 2024) 34% 10. Claude 3.5 Haiku 32% 11. Gemini 2.0 Flash (Feb 2025) 30% 12. GPT-4o 26% 13. GPT-4.1 mini 16% 14. Claude 3 Haiku 12% 15. 020406080 Sponsored placements are available on pages like this one. [Advertise on Noometry](https://noometry.com/advertise) ## All results CadEval results by model | # | Model | Provider | Score | Setting | Source | Date | | --- | --- | --- | --- | --- | --- | --- | | 1 | [o3](https://noometry.com/models/o3) | [OpenAI](https://noometry.com/providers/openai) | 74% | medium | [Epoch AI](https://epoch.ai/benchmarks) | | | 2 | [Gemini 2.5 Pro](https://noometry.com/models/gemini-2-5-pro) | [![](/logos/google.svg) Google](https://noometry.com/providers/google) | 64% | | [Epoch AI](https://epoch.ai/benchmarks) | | | 3 | [o4-mini](https://noometry.com/models/o4-mini) | [OpenAI](https://noometry.com/providers/openai) | 62% | medium | [Epoch AI](https://epoch.ai/benchmarks) | | | 4 | [o1](https://noometry.com/models/o1) | [OpenAI](https://noometry.com/providers/openai) | 56% | medium | [Epoch AI](https://epoch.ai/benchmarks) | | | 5 | [Claude 3.7 Sonnet](https://noometry.com/models/claude-3-7-sonnet) | [Anthropic](https://noometry.com/providers/anthropic) | 54% | | [Epoch AI](https://epoch.ai/benchmarks) | | | 6 | [o3-mini](https://noometry.com/models/o3-mini) | [OpenAI](https://noometry.com/providers/openai) | 54% | medium | [Epoch AI](https://epoch.ai/benchmarks) | | | 7 | [Claude 3.5 Sonnet](https://noometry.com/models/claude-3-5-sonnet) | [Anthropic](https://noometry.com/providers/anthropic) | 48% | | [Epoch AI](https://epoch.ai/benchmarks) | | | 8 | [GPT-4.1](https://noometry.com/models/gpt-4-1) | [OpenAI](https://noometry.com/providers/openai) | 42% | | [Epoch AI](https://epoch.ai/benchmarks) | | | 9 | [Gemini 1.5 Pro (May 2024)](https://noometry.com/models/gemini-1-5-pro) | [![](/logos/google.svg) Google](https://noometry.com/providers/google) | 34% | | [Epoch AI](https://epoch.ai/benchmarks) | | | 10 | [Claude 3.5 Haiku](https://noometry.com/models/claude-3-5-haiku) | [Anthropic](https://noometry.com/providers/anthropic) | 32% | | [Epoch AI](https://epoch.ai/benchmarks) | | | 11 | [Gemini 2.0 Flash (Feb 2025)](https://noometry.com/models/gemini-2-0-flash) | [![](/logos/google.svg) Google](https://noometry.com/providers/google) | 30% | | [Epoch AI](https://epoch.ai/benchmarks) | | | 12 | [GPT-4o](https://noometry.com/models/gpt-4o) | [OpenAI](https://noometry.com/providers/openai) | 26% | | [Epoch AI](https://epoch.ai/benchmarks) | | | 13 | [GPT-4.1 mini](https://noometry.com/models/gpt-4-1-mini) | [OpenAI](https://noometry.com/providers/openai) | 16% | | [Epoch AI](https://epoch.ai/benchmarks) | | | 14 | [Claude 3 Haiku](https://noometry.com/models/claude-3-haiku) | [Anthropic](https://noometry.com/providers/anthropic) | 12% | | [Epoch AI](https://epoch.ai/benchmarks) | | ## Compare the leaders - [o3 vs Gemini 2.5 Pro](https://noometry.com/compare/gemini-2-5-pro-vs-o3) - [o3 vs o4-mini](https://noometry.com/compare/o3-vs-o4-mini) - [o3 vs o1](https://noometry.com/compare/o1-vs-o3) - [o3 vs Claude 3.7 Sonnet](https://noometry.com/compare/claude-3-7-sonnet-vs-o3) - [Gemini 2.5 Pro vs o4-mini](https://noometry.com/compare/gemini-2-5-pro-vs-o4-mini) - [Gemini 2.5 Pro vs o1](https://noometry.com/compare/gemini-2-5-pro-vs-o1) ## Other coding benchmarks - [SWE-bench Verified](https://noometry.com/benchmarks/swe-bench-verified) - [DeepSWE](https://noometry.com/benchmarks/deepswe) - [FrontierCode](https://noometry.com/benchmarks/frontiercode) - [SWE-bench Verified (bash only)](https://noometry.com/benchmarks/swe-bench-bash-only) - [Aider Polyglot](https://noometry.com/benchmarks/aider-polyglot) - [LMArena WebDev](https://noometry.com/benchmarks/arena-webdev) - [CursorBench](https://noometry.com/benchmarks/cursorbench) - [SWE-bench Multilingual](https://noometry.com/benchmarks/swe-bench-multilingual) - [FrontierSWE](https://noometry.com/benchmarks/frontierswe) - [SciCode](https://noometry.com/benchmarks/scicode) - [GSO](https://noometry.com/benchmarks/gso-bench) - [WeirdML](https://noometry.com/benchmarks/weirdml) ## Frequently asked questions ### What does CadEval measure? Generating CAD code for 3D parts from text descriptions. ### Which model has the highest CadEval score? As of October 2026, o3 has the highest published CadEval score on Noometry at 74%, out of 14 models with results. ### Cite this page Noometry. (2026). CadEval leaderboard. Retrieved October 10, 2026, from https://noometry.com/benchmarks/cadeval Quote Noometry with a link back to this page. It is also available in [Markdown](https://noometry.com/md/benchmarks/cadeval.md).