Llama 2 7B Chat Flan2022 1.2M: benchmark results
Provider: Meta.
Aggregate Rating 1287 ± 35, rank #8895 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - HellaSwag | 76.25 | Normalized accuracy (%) (10-shot) | 28.3 |
| Open LLM Leaderboard v1 - WinoGrande | 71.82 | Accuracy (%) (5-shot) | 27.4 |
| Open LLM Leaderboard v1 - MMLU | 45.99 | Accuracy (%) (5-shot) | 24.5 |
| Open LLM Leaderboard v1 - ARC Challenge | 49.57 | Normalized accuracy (%) (25-shot) | 24.1 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 42.17 | MC2 (%) (0-shot) | 19.6 |
| Open LLM Leaderboard v1 - GSM8K | 1.52 | Accuracy (%) (5-shot) | 17.3 |
Interactive version: theaggregate.ai/model?slug=llama-2-7b-chat-flan2022-1-2m · How It Works · Data refreshed daily, snapshot 2026-11-08.