Agentic coding focus, 1M context, strong multimodal performance
| Benchmark | Score | Rank |
|---|---|---|
SWE-bench Real-world GitHub issue resolution | 78.8% | #8 / 39 |
Terminal Agentic terminal coding tasks requiring multi-step execution | 61.6% | #13 / 56 |
LiveCodeBenchvals.ai Contamination-free competitive programming (filtered by cutoff date) | 86% | #16 / 54 |
Arena Elo Human preference ranking via blind comparisons | 1470 | #17 / 51 |
MMMUvals.ai College-level multimodal reasoning across 30+ disciplines | 84.2% | #17 / 53 |
MMLU-Provals.ai Harder 10-option successor to MMLU; more reasoning-focused | 87.7% | #18 / 52 |
GPQAArtificial Analysis PhD-level science questions even experts struggle with | 88.2% | #35 / 81 |
hleArtificial Analysis | 25.7% | #41 / 69 |