| Benchmark | Domain | Score | vs best recorded | Setting | Run | Source |
|---|---|---|---|---|---|---|
| BBH | reasoning | 52.5% | 59% | — | — | External ↗ |
| GSM8K | math | 62.9% | 67% | — | — | External ↗ |
| PIQA | other | 80.3% | 91% | — | — | External ↗ |
| HellaSwag | reasoning | 78.1% | 82% | — | — | External ↗ |
| ARC AI2 | other | 81.7% | 86% | — | — | External ↗ |
| LAMBADA | other | 71.8% | 90% | — | — | 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.