CodeLlama-13B-hf (Publisher: codellama): benchmark results
Provider: Meta.
Aggregate Rating 1218 ± 36, rank #9494 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - GSM8K | 12.13 | Accuracy (%) (5-shot) | 33.8 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 43.79 | MC2 (%) (0-shot) | 24.8 |
| Open LLM Leaderboard v1 - WinoGrande | 67.17 | Accuracy (%) (5-shot) | 21.2 |
| Open LLM Leaderboard v1 - MMLU | 32.81 | Accuracy (%) (5-shot) | 17.5 |
| Open LLM Leaderboard v1 - ARC Challenge | 40.87 | Normalized accuracy (%) (25-shot) | 17.2 |
| Open LLM Leaderboard v1 - HellaSwag | 63.35 | Normalized accuracy (%) (10-shot) | 16.5 |
Interactive version: theaggregate.ai/model?slug=codellama-13b-hf-publisher-codellama · How It Works · Data refreshed daily, snapshot 2026-11-08.