| Benchmark | Domain | Score | vs best recorded | Setting | Run | Source |
|---|---|---|---|---|---|---|
| BBH | reasoning | 35.2% | 39% | — | — | External ↗ |
| GSM8K | math | 17.7% | 19% | — | — | External ↗ |
| MMLU | knowledge | 42.3% | 48% | — | — | External ↗ |
| PIQA | other | 77.3% | 87% | — | — | External ↗ |
| Winogrande | other | 65.4% | 73% | — | — | External ↗ |
| HellaSwag | reasoning | 71.4% | 75% | — | — | External ↗ |
| ARC AI2 | other | 42.1% | 44% | — | — | External ↗ |
| TriviaQA | other | 53.2% | 61% | — | — | 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.