CodeLlama-13B-Python: benchmark results
Provider: Meta.
Aggregate Rating 1318 ± 52, rank #8363 of 10916 rated models, from 11 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| ENAMEL | 21.6 | Greedy eff@1 (%) (imported) | 51.7 |
| EvoEval Tool Use | 48 | Pass@1 (%) | 51 |
| BigCode Models Leaderboard | 42.9 | HumanEval Python Pass@1 (%) | 47.5 |
| EvoEval Creative | 24 | Pass@1 (%) | 46 |
| CRUXEval | 39.8 | Output Prediction pass@1 (%) | 40.5 |
| EvoEval Concise | 46.95 | Pass@1 (%) | 39 |
| EvoEval Difficult | 18 | Pass@1 (%) | 36 |
| EvoEval Combine | 6 | Pass@1 (%) | 34 |
| EvoEval | 32.53 | Pass@1 (%) | 32 |
| EvoEval Subtle | 38 | Pass@1 (%) | 23 |
| EvoEval Verbose | 36.59 | Pass@1 (%) | 18 |
Interactive version: theaggregate.ai/model?slug=codellama-13b-python · How It Works · Data refreshed daily, snapshot 2026-11-08.