CodeLlama-7B-Python: benchmark results
Provider: Meta.
Aggregate Rating 1278 ± 43, rank #8999 of 10916 rated models, from 15 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| ENAMEL | 24.7 | Greedy eff@1 (%) (imported) | 55.2 |
| BigCode Models Leaderboard | 40.5 | HumanEval Python Pass@1 (%) | 44.1 |
| EvoEval Subtle | 42 | Pass@1 (%) | 34 |
| EvoEval Verbose | 43.9 | Pass@1 (%) | 34 |
| EvoEval Tool Use | 44 | Pass@1 (%) | 32 |
| Big Code Memorization - HumanEval pass@1 | 38.41 | HumanEval pass@1 (%) | 29.4 |
| Big Code Memorization - HumanEval pass@50 | 30.62 | HumanEval pass@50 (%) | 29.4 |
| Big Code Memorization - HumanEval-ET pass@1 | 33.54 | HumanEval-ET pass@1 (%) | 29.4 |
| Big Code Memorization - HumanEval-ET pass@50 | 25.68 | HumanEval-ET pass@50 (%) | 29.4 |
| CRUXEval | 35.9 | Output Prediction pass@1 (%) | 28.6 |
| EvoEval Concise | 36.59 | Pass@1 (%) | 25 |
| EvoEval | 29.27 | Pass@1 (%) | 24 |
Interactive version: theaggregate.ai/model?slug=codellama-7b-python · How It Works · Data refreshed daily, snapshot 2026-11-08.