Open-weight multimodal MoE trained jointly on text, images, audio, and video.
| Benchmark | Score | Rank |
|---|---|---|
LiveCodeBenchvals.ai Contamination-free competitive programming (filtered by cutoff date) | 85.9% | #23 / 62 |
MMLU-Provals.ai Harder 10-option successor to MMLU; more reasoning-focused | 86.3% | #38 / 61 |
MMMUvals.ai College-level multimodal reasoning across 30+ disciplines | 78.5% | #40 / 51 |
GPQAArtificial Analysis PhD-level science questions even experts struggle with | 89.5% | #43 / 95 |
hleArtificial Analysis | 33.3% | #46 / 85 |