Llama 2 7B Chat V4 [bfloat16] [rev: 405c54ec7aea]: benchmark results
Provider: Meta. Access: Open.
Aggregate Rating 1302 ± 35, rank #8695 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - WinoGrande | 74.03 | Accuracy (%) (5-shot) | 34.6 |
| Open LLM Leaderboard v1 - HellaSwag | 78.56 | Normalized accuracy (%) (10-shot) | 34.4 |
| Open LLM Leaderboard v1 - ARC Challenge | 53.41 | Normalized accuracy (%) (25-shot) | 29.4 |
| Open LLM Leaderboard v1 - GSM8K | 7.51 | Accuracy (%) (5-shot) | 27 |
| Open LLM Leaderboard v1 - MMLU | 46.43 | Accuracy (%) (5-shot) | 24.9 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 38.71 | MC2 (%) (0-shot) | 8.8 |
Interactive version: theaggregate.ai/model?slug=llama-2-7b-chat-v4-bfloat16-rev-405c54ec7aea · How It Works · Data refreshed daily, snapshot 2026-11-08.