| Benchmark | Domain | Score | vs best recorded | Setting | Run | Source |
|---|---|---|---|---|---|---|
| BBH | reasoning | 47.2% | 53% | — | — | External ↗ |
| GSM8K | math | 44.9% | 48% | — | — | External ↗ |
| MMLU | knowledge | 64.0% | 73% | — | — | External ↗ |
| Winogrande | other | 71.3% | 80% | — | — | External ↗ |
| HellaSwag | reasoning | 74.4% | 78% | — | — | External ↗ |
| ARC AI2 | other | 50.3% | 53% | — | — | 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.