CodeLlama-34B-Instruct-hf [float16] [rev: c109b9dde086]: benchmark results
Provider: Meta. Access: Open.
Aggregate Rating 1256 ± 40, rank #9200 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - GSM8K | 31.01 | Accuracy (%) (5-shot) | 47.9 |
| Open LLM Leaderboard v1 - WinoGrande | 74.51 | Accuracy (%) (5-shot) | 37 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 44.29 | MC2 (%) (0-shot) | 26.6 |
| Open LLM Leaderboard v1 - MMLU | 39.72 | Accuracy (%) (5-shot) | 20.9 |
| Open LLM Leaderboard v1 - ARC Challenge | 40.78 | Normalized accuracy (%) (25-shot) | 17.1 |
| Open LLM Leaderboard v1 - HellaSwag | 35.66 | Normalized accuracy (%) (10-shot) | 7.1 |
Interactive version: theaggregate.ai/model?slug=codellama-34b-instruct-hf-float16-rev-c109b9dde086 · How It Works · Data refreshed daily, snapshot 2026-11-08.