humaneval
Unknown
OCR benchmark
5
Total Results
5
Models Tested
1
Metrics
2025-12-21
Last Updated
pass@1
Higher is better
| Rank | Model | Score | Source |
|---|---|---|---|
| 1 | o1-preview Classic Python code generation benchmark. | 92.4 | openai-blog |
| 2 | claude-35-sonnet | 92 | anthropic-blog |
| 3 | gpt-4o | 90.2 | openai-blog |
| 4 | deepseek-v3 | 82.6 | deepseek-blog |
| 5 | llama-3-70b | 81.7 | meta-blog |