| Benchmark | Model | Rank | Results |
|---|---|---|---|
| code-generation-on-swe-bench-verified | MiniMax-M2.5 (Claude Code) | #8 | Accuracy: 80.2 |
| deep-research-agents-on-browsecomp | MiniMax-M2.5 | #19 | Accuracy: 76.3 |
| code-generation-on-swe-bench-pro | MiniMax-M2.5 | #25 | Resolved: 55.4 |
| question-answering-on-humanity-s-last-exam-hle | MiniMax-M2.5 | #29 | Accuracy: 19.4 |
| multiple-choice-question-answering-mcqa-on-gpqa-diamond | MiniMax-M2.5 | #37 | Accuracy: 85.2 |