Llama 2 7B Structural Prune 1.5x: benchmark results
Provider: Meta.
Aggregate Rating 1188 ± 37, rank #9681 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - ARC Challenge | 42.92 | Normalized accuracy (%) (25-shot) | 18.9 |
| Open LLM Leaderboard v1 - HellaSwag | 64.86 | Normalized accuracy (%) (10-shot) | 17 |
| Open LLM Leaderboard v1 - WinoGrande | 64.01 | Accuracy (%) (5-shot) | 16.8 |
| Open LLM Leaderboard v1 - MMLU | 29.31 | Accuracy (%) (5-shot) | 16.3 |
| Open LLM Leaderboard v1 - GSM8K | 1.14 | Accuracy (%) (5-shot) | 15.7 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 40.41 | MC2 (%) (0-shot) | 14.1 |
Interactive version: theaggregate.ai/model?slug=llama-2-7b-structural-prune-1-5x · How It Works · Data refreshed daily, snapshot 2026-11-08.