Llama 2. 7B Zh: benchmark results
Provider: Meta.
Aggregate Rating 1346 ± 40, rank #7807 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - MMLU | 60.69 | Accuracy (%) (5-shot) | 49.3 |
| Open LLM Leaderboard v1 - WinoGrande | 71.74 | Accuracy (%) (5-shot) | 27.2 |
| Open LLM Leaderboard v1 - ARC Challenge | 52.05 | Normalized accuracy (%) (25-shot) | 26.6 |
| Open LLM Leaderboard v1 - GSM8K | 6.44 | Accuracy (%) (5-shot) | 25.6 |
| Open LLM Leaderboard v1 - HellaSwag | 74.88 | Normalized accuracy (%) (10-shot) | 25.5 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 42.86 | MC2 (%) (0-shot) | 21.8 |
Interactive version: theaggregate.ai/model?slug=llama-2-7b-zh · How It Works · Data refreshed daily, snapshot 2026-11-08.