Mistral-7B-Instruct-v0.2-sparsity-20: benchmark results
Provider: Mistral.
Aggregate Rating 1301 ± 33, rank #8712 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 47.22 | MC2 (%) (0-shot) | 36.9 |
| Open LLM Leaderboard v1 - GSM8K | 11.3 | Accuracy (%) (5-shot) | 32.7 |
| Open LLM Leaderboard v1 - HellaSwag | 76.71 | Normalized accuracy (%) (10-shot) | 29.4 |
| Open LLM Leaderboard v1 - ARC Challenge | 52.65 | Normalized accuracy (%) (25-shot) | 27.5 |
| Open LLM Leaderboard v1 - MMLU | 47.27 | Accuracy (%) (5-shot) | 26.2 |
| Open LLM Leaderboard v1 - WinoGrande | 69.06 | Accuracy (%) (5-shot) | 23.1 |
Interactive version: theaggregate.ai/model?slug=mistral-7b-instruct-v0-2-sparsity-20 · How It Works · Data refreshed daily, snapshot 2026-11-08.