CodeLlama-7B-Python-hf: benchmark results
Meta's CodeLlama 7B Python, the Python-specialized code model in the Llama 2-based CodeLlama family, released under the Llama 2 Community License; the linked card provides no further details here. Provider: Meta. Released 2023-08-24. Access: Open.
Aggregate Rating 1169 ± 14, rank #1608 of 1656 rated models, from 72 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| MMLU-by-task - College Physics | 35.29 | Accuracy (%) | 88.7 |
| MMLU-by-task - High School Physics | 35.1 | Accuracy (%) | 82 |
| ToolBench - Google Sheets | 49.13 | Task Score | 79.1 |
| MMLU-by-task - High School Statistics | 46.3 | Accuracy (%) | 78.9 |
| ToolBench - Home Search | 83 | Task Score | 74.4 |
| ToolBench - The Cat API | 88 | Task Score | 74.4 |
| ToolBench - Trip Booking | 68.33 | Task Score | 72.1 |
| ToolBench Leaderboard | 52.15 | Average Task Score | 72.1 |
| MMLU-by-task - College Chemistry | 39 | Accuracy (%) | 70.3 |
| ToolBench - Tabletop | 22.86 | Task Score | 69.8 |
| ToolBench - VirtualHome | 21.33 | Task Score | 67.4 |
| ToolBench - WebShop Short | 1.58 | Task Score | 58.1 |
Interactive version: theaggregate.ai/model?slug=codellama-7b-python-hf · How It Works · Data refreshed daily, snapshot 2026-10-20.