TinyMistral-248M-v2.5-Instruct: benchmark results
Provider: Other. Access: Open.
Aggregate Rating 1077 ± 43, rank #10815 of 10870 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 44.21 | MC2 (%) (0-shot) | 26.3 |
| Open LLM Leaderboard v1 - GSM8K | 0 | Accuracy (%) (5-shot) | 4.6 |
| Open LLM Leaderboard v1 - HellaSwag | 27.6 | Normalized accuracy (%) (10-shot) | 4.3 |
| Open LLM Leaderboard v1 - MMLU | 23.9 | Accuracy (%) (5-shot) | 2.6 |
| Open LLM Leaderboard v1 - ARC Challenge | 22.27 | Normalized accuracy (%) (25-shot) | 1 |
| Open LLM Leaderboard v1 - WinoGrande | 48.22 | Accuracy (%) (5-shot) | 0.3 |
Interactive version: theaggregate.ai/model?slug=tinymistral-248m-v2-5-instruct · How It Works · Data refreshed daily, snapshot 2026-11-12.