Mistral-7B-Instruct-adapt-v0.21 [float16] [Adapter] [rev: 15f7ace07356]: benchmark results
Provider: Mistral. Access: Open.
Aggregate Rating 1469 ± 43, rank #2874 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - ARC Challenge | 73.98 | Normalized accuracy (%) (25-shot) | 98.7 |
| Open LLM Leaderboard v1 - HellaSwag | 88.61 | Normalized accuracy (%) (10-shot) | 93 |
| Open LLM Leaderboard v1 - WinoGrande | 84.29 | Accuracy (%) (5-shot) | 92.8 |
| Open LLM Leaderboard v1 - GSM8K | 70.28 | Accuracy (%) (5-shot) | 92.3 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 69.76 | MC2 (%) (0-shot) | 89.4 |
| Open LLM Leaderboard v1 - MMLU | 64.81 | Accuracy (%) (5-shot) | 77 |
Interactive version: theaggregate.ai/model?slug=mistral-7b-instruct-adapt-v0-21-float16-adapter-rev-15f7ace07356 · How It Works · Data refreshed daily, snapshot 2026-11-08.