Agentic coding focus, 1M context, strong multimodal performance
| Benchmark | Score | Rank |
|---|---|---|
Terminal Agentic terminal coding tasks requiring multi-step execution | 61.6% | #5 / 37 |
MMMUvals.ai College-level multimodal reasoning across 30+ disciplines | 84.2% | #6 / 33 |
MMLU-Provals.ai Harder 10-option successor to MMLU; more reasoning-focused | 87.7% | #7 / 30 |
SWE-bench Real-world GitHub issue resolution | 78.8% | #8 / 38 |
Arena Elo Human preference ranking via blind comparisons | 1470 | #8 / 41 |
GPQAArtificial Analysis PhD-level science questions even experts struggle with | 88.2% | #12 / 54 |