CodeLlama-70B: benchmark results
Provider: Meta.
Aggregate Rating 1319 ± 50, rank #8348 of 10916 rated models, from 7 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Big Code Memorization - HumanEval-ET pass@1 | 45.12 | HumanEval-ET pass@1 (%) | 70.6 |
| Big Code Memorization - HumanEval pass@1 | 52.44 | HumanEval pass@1 (%) | 64.7 |
| Big Code Memorization - HumanEval pass@50 | 43.17 | HumanEval pass@50 (%) | 64.7 |
| Big Code Memorization - HumanEval-ET pass@50 | 36.15 | HumanEval-ET pass@50 (%) | 64.7 |
| BigCode Models Leaderboard | 52.4 | HumanEval Python Pass@1 (%) | 64.4 |
| EvalPlus (HumanEval+ & MBPP+) | 50.6 | Pass@1 avg (%) | 46.8 |
| OJBench | 2.53 | Score (imported) | 5.9 |
Interactive version: theaggregate.ai/model?slug=codellama-70b-d7b3lj · How It Works · Data refreshed daily, snapshot 2026-11-08.