CodeLlama-7B-hf [4bit]: benchmark results
Provider: Meta. Access: Open.
Aggregate Rating 1196 ± 33, rank #9642 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - GSM8K | 5.16 | Accuracy (%) (5-shot) | 23.8 |
| Open LLM Leaderboard v1 - MMLU | 31.12 | Accuracy (%) (5-shot) | 17 |
| Open LLM Leaderboard v1 - WinoGrande | 64.01 | Accuracy (%) (5-shot) | 16.8 |
| Open LLM Leaderboard v1 - ARC Challenge | 39.93 | Normalized accuracy (%) (25-shot) | 16.2 |
| Open LLM Leaderboard v1 - HellaSwag | 60.8 | Normalized accuracy (%) (10-shot) | 14.7 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 37.82 | MC2 (%) (0-shot) | 6.7 |
Interactive version: theaggregate.ai/model?slug=codellama-7b-hf-4bit · How It Works · Data refreshed daily, snapshot 2026-11-08.