TinyMistral-248M-v2.5: benchmark results
Provider: Other. Access: Open.
Unified ELO 1192 ± 20, rank #2910 of 2928 rated models, from 12 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 46.72 | MC2 (%) (0-shot) | 35.3 |
| Open LLM Leaderboard - MuSR | 37.82 | Score | 28.7 |
| Open LLM Leaderboard - MATH Level 5 | 0.98 | Score | 7 |
| Open LLM Leaderboard - BBH | 30.39 | Score | 6.1 |
| Open LLM Leaderboard - GPQA | 25.08 | Score | 5.5 |
| Open LLM Leaderboard - MMLU-Pro | 11.35 | Score | 5.3 |
| Open LLM Leaderboard v1 - GSM8K | 0 | Accuracy (%) (5-shot) | 4.6 |
| Open LLM Leaderboard v1 - HellaSwag | 27.49 | Normalized accuracy (%) (10-shot) | 4.2 |
| Open LLM Leaderboard v1 - ARC Challenge | 24.57 | Normalized accuracy (%) (25-shot) | 3.8 |
| Open LLM Leaderboard - IFEval | 13.36 | Score | 3.3 |
| Open LLM Leaderboard v1 - MMLU | 23.15 | Accuracy (%) (5-shot) | 1.7 |
| Open LLM Leaderboard v1 - WinoGrande | 47.83 | Accuracy (%) (5-shot) | 0.1 |
Interactive version: theaggregate.ai/model?slug=tinymistral-248m-v2-5 · How It Works · Data refreshed daily, snapshot 2026-09-23.