Mistral-7B-summ-ia3-pruned20 [Adapter]: benchmark results
Provider: Mistral. Access: Open.
Aggregate Rating 1398 ± 34, rank #6211 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 67.84 | MC2 (%) (0-shot) | 86.7 |
| Open LLM Leaderboard v1 - HellaSwag | 84.77 | Normalized accuracy (%) (10-shot) | 68.4 |
| Open LLM Leaderboard v1 - ARC Challenge | 62.88 | Normalized accuracy (%) (25-shot) | 60.2 |
| Open LLM Leaderboard v1 - GSM8K | 38.82 | Accuracy (%) (5-shot) | 53.6 |
| Open LLM Leaderboard v1 - WinoGrande | 76.95 | Accuracy (%) (5-shot) | 52 |
| Open LLM Leaderboard v1 - MMLU | 60.09 | Accuracy (%) (5-shot) | 46.9 |
Interactive version: theaggregate.ai/model?slug=mistral-7b-summ-ia3-pruned20-adapter · How It Works · Data refreshed daily, snapshot 2026-11-08.