CodeLlama-34B-Instruct — benchmark results
Provider: Meta. Access: Open.
Unified ELO 1101 ± 120, rank #1708 of 1721 rated models, from 9 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| SecCodePLT | 67.88 | Score (%) | 100 |
| InfiBench | 50.45 | Score (%) | 79 |
| BigCode Models Leaderboard | 50.8 | HumanEval Python Pass@1 (%) | 60.2 |
| CyberSecEval | 36.33 | Average Injection Success Rate (self-reported) | 50 |
| BigCodeBench | 29 | Pass@1 (%) | 14.3 |
| FullStackBench en | 29.22 | Score (self-reported) | 11.1 |
| Chatbot Arena (Text) | 1136 | Elo | 7.9 |
| SEAL - Coding | 598 | Score | 0 |
| SEAL - Math | 37.51 | Score | 0 |
Interactive version: aibenchmarks.dev/model?slug=codellama-34b-instruct · How the rankings work · Data refreshed daily, snapshot 2026-07-06.