mistral-sft-v3: benchmark results
Provider: Mistral. Access: Open.
Aggregate Rating 1399 ± 33, rank #6134 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - MMLU | 63.4 | Accuracy (%) (5-shot) | 60.4 |
| Open LLM Leaderboard v1 - WinoGrande | 77.66 | Accuracy (%) (5-shot) | 57.6 |
| Open LLM Leaderboard v1 - ARC Challenge | 61.35 | Normalized accuracy (%) (25-shot) | 52.5 |
| Open LLM Leaderboard v1 - HellaSwag | 82.23 | Normalized accuracy (%) (10-shot) | 49.7 |
| Open LLM Leaderboard v1 - GSM8K | 32.45 | Accuracy (%) (5-shot) | 48.8 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 48.49 | MC2 (%) (0-shot) | 41.4 |
Interactive version: theaggregate.ai/model?slug=mistral-sft-v3 · How It Works · Data refreshed daily, snapshot 2026-11-08.