CodeLlama-34B-Instruct: benchmark results
Provider: Meta. Released 2023-08-24.
Aggregate Rating 1338 ± 26, rank #8004 of 10916 rated models, from 59 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| MERA Code - YABLoCo | 12.02 | pass@1 (%) | 89.2 |
| BigCode Models Leaderboard | 50.8 | HumanEval Python Pass@1 (%) | 60.2 |
| EvoEval Creative | 27 | Pass@1 (%) | 56 |
| EvoEval Difficult | 22 | Pass@1 (%) | 53 |
| CyberSecEval | 36.33 | Average Injection Success Rate (imported) | 50 |
| EvoEval Concise | 50 | Pass@1 (%) | 48 |
| EvoEval Tool Use | 47 | Pass@1 (%) | 47 |
| MERA Code - UnitTests | 17.57 | CodeBLEU (%) | 46.2 |
| EvoEval Combine | 9 | Pass@1 (%) | 44 |
| EvoEval | 36.26 | Pass@1 (%) | 42 |
| EvoEval Subtle | 43 | Pass@1 (%) | 38 |
| MERA Code - ruCodeReviewer | 2.32 | Top-1 Accuracy (%) | 35.4 |
Interactive version: theaggregate.ai/model?slug=codellama-34b-instruct · How It Works · Data refreshed daily, snapshot 2026-11-08.