| Benchmark | Domain | Score | vs best recorded | Setting | Run | Source |
|---|---|---|---|---|---|---|
| BBH | reasoning | 34.8% | 39% | — | — | External ↗ |
| GSM8K | math | 38.6% | 41% | — | — | External ↗ |
| MMLU | knowledge | 49.9% | 57% | — | — | External ↗ |
| Winogrande | other | 65.8% | 74% | — | — | External ↗ |
| HellaSwag | reasoning | 71.4% | 75% | — | — | External ↗ |
| ARC AI2 | other | 54.5% | 57% | — | — | External ↗ |
Source: Epoch AI Benchmarking Hub (CC BY 4.0). “External” rows are leaderboard results Epoch collects from third parties. Best reported setting per benchmark is shown.
0 observations (OpenRouter listing). History accumulates with every ingest run; a single point means no change has been observed yet.