Thestral-v0.2: benchmark results
Provider: Other.
Aggregate Rating 1402 ± 33, rank #5965 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - GSM8K | 45.94 | Accuracy (%) (5-shot) | 59.7 |
| Open LLM Leaderboard v1 - ARC Challenge | 62.71 | Normalized accuracy (%) (25-shot) | 59.4 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 52.77 | MC2 (%) (0-shot) | 57.3 |
| Open LLM Leaderboard v1 - MMLU | 62.73 | Accuracy (%) (5-shot) | 56.5 |
| Open LLM Leaderboard v1 - HellaSwag | 82.49 | Normalized accuracy (%) (10-shot) | 51.6 |
| Open LLM Leaderboard v1 - WinoGrande | 75.77 | Accuracy (%) (5-shot) | 44 |
Interactive version: theaggregate.ai/model?slug=thestral-v0-2 · How It Works · Data refreshed daily, snapshot 2026-11-08.