Llama 2 7B Chat 30 Attention Sparsity: benchmark results
Provider: Meta. Access: Open.
Aggregate Rating 1307 ± 33, rank #8605 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - GSM8K | 17.44 | Accuracy (%) (5-shot) | 39 |
| Open LLM Leaderboard v1 - HellaSwag | 76.87 | Normalized accuracy (%) (10-shot) | 29.7 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 45.02 | MC2 (%) (0-shot) | 29.5 |
| Open LLM Leaderboard v1 - ARC Challenge | 53.41 | Normalized accuracy (%) (25-shot) | 29.4 |
| Open LLM Leaderboard v1 - MMLU | 47.04 | Accuracy (%) (5-shot) | 25.9 |
| Open LLM Leaderboard v1 - WinoGrande | 71.03 | Accuracy (%) (5-shot) | 25.8 |
Interactive version: theaggregate.ai/model?slug=llama-2-7b-chat-30-attention-sparsity · How It Works · Data refreshed daily, snapshot 2026-11-08.