Meta's first proprietary model from Superintelligence Labs, non-open-weight
| Benchmark | Score | Rank |
|---|---|---|
MMMUvals.ai College-level multimodal reasoning across 30+ disciplines | 87.4% | #8 / 46 |
hleArtificial Analysis | 39.9% | #12 / 61 |
Arena Elo Human preference ranking via blind comparisons | 1480 | #15 / 51 |
MMLU-Provals.ai Harder 10-option successor to MMLU; more reasoning-focused | 87.3% | #20 / 45 |
TerminalArtificial Analysis Agentic terminal coding tasks requiring multi-step execution | 45.5% | #22 / 56 |
GPQAArtificial Analysis PhD-level science questions even experts struggle with | 88.4% | #28 / 73 |