Open-weight multimodal MoE optimized for efficient local and hosted deployment.
| Benchmark | Score | Rank |
|---|---|---|
ARC-AGIARC Prize Novel reasoning tasks requiring fluid intelligence | 40.1% | #21 / 33 |
GPQAArtificial Analysis PhD-level science questions even experts struggle with | 89.5% | #44 / 95 |
hleArtificial Analysis | 33.3% | #47 / 85 |