| instruction-following-on-multi-if | MiniCPM5-1B (Thinking) | #10 | Accuracy: 43.54 |
| mathematical-reasoning-on-hmmt-feb-2026 | MiniCPM5-1B (Thinking) | #11 | Accuracy: 25.76 |
| agents-on-bfclv4 | MiniCPM5-1B (Thinking) | #15 | Accuracy: 25.15 |
| instruction-following-on-multichallenge | MiniCPM5-1B (Thinking) | #16 | Accuracy: 19.48 |
| multiple-choice-question-answering-mcqa-on-supergpqa | MiniCPM5-1B (Thinking) | #22 | Accuracy: 23.14 |
| multi-task-language-understanding-on-mmlu-redux | MiniCPM5-1B (Thinking) | #34 | Accuracy: 70.06 |
| instruction-following-on-ifbench | MiniCPM5-1B (Thinking) | #39 | Accuracy: 46.67 |
| mathematical-reasoning-on-aime-2026 | MiniCPM5-1B (Thinking) | #48 | Accuracy: 40.42 |
| mathematical-reasoning-on-math-500 | MiniCPM5-1B (Thinking) | #51 | Accuracy: 91.6 |
| code-generation-on-livecodebench-v6 | MiniCPM5-1B (Thinking) | #73 | Pass@1: 0.3352 |
| mathematical-reasoning-on-aime-2025 | MiniCPM5-1B (Thinking) | #97 | Accuracy: 40.42 |
| multi-task-language-understanding-on-mmlu-pro | MiniCPM5-1B (Thinking) | #116 | Accuracy: 48.85 |
| multiple-choice-question-answering-mcqa-on-gpqa-diamond | MiniCPM5-1B (Thinking) | #133 | Accuracy: 26.26 |