Metis-0.5: benchmark results
Provider: Mihaiii. Access: Open.
Aggregate Rating 1398 ± 33, rank #6191 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - HellaSwag | 83.77 | Normalized accuracy (%) (10-shot) | 61.3 |
| Open LLM Leaderboard v1 - ARC Challenge | 62.63 | Normalized accuracy (%) (25-shot) | 59 |
| Open LLM Leaderboard v1 - GSM8K | 42.91 | Accuracy (%) (5-shot) | 57.3 |
| Open LLM Leaderboard v1 - MMLU | 62.16 | Accuracy (%) (5-shot) | 54.3 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 49.33 | MC2 (%) (0-shot) | 44.4 |
| Open LLM Leaderboard v1 - WinoGrande | 75.14 | Accuracy (%) (5-shot) | 40.5 |
Interactive version: theaggregate.ai/model?slug=metis-0-5 · How It Works · Data refreshed daily, snapshot 2026-11-08.