| instruction-following-on-multi-if | MiniCPM5-2B | #6 | Accuracy: 71.8 |
| social-commonsense-reasoning-on-siqa | MiniCPM-1.2B (Math-L3) | #8 | Accuracy: 43.35 |
| mathematical-reasoning-on-hmmt-feb-2026 | MiniCPM5-2B | #9 | Accuracy: 63.8 |
| multiple-choice-question-answering-mcqa-on-supergpqa | MiniCPM5-2B | #18 | Accuracy: 40.8 |
| instruction-following-on-ifbench | MiniCPM5-2B | #25 | Accuracy: 66.3 |
| multi-task-language-understanding-on-mmlu-redux | MiniCPM5-2B | #26 | Accuracy: 84.7 |
| mathematical-reasoning-on-aime-2025 | MiniCPM5-2B | #30 | Accuracy: 86.5 |
| multi-task-language-understanding-on-mmlu-pro | MiniCPM5-2B | #71 | Accuracy: 70.8 |
| common-sense-reasoning-on-arc-easy | MiniCPM-1.2B (Math-L3) | #78 | Accuracy: 59.79 |
| common-sense-reasoning-on-winogrande | MiniCPM-1.2B (Math-L3) | #125 | Accuracy: 59.04 |
| mathematical-reasoning-on-math-500 | MiniCPM-1.2B (Math-L3) | #129 | Accuracy: 37.02 |
| sentence-completion-on-hellaswag | MiniCPM-1.2B (Math-L3) | #159 | Accuracy: 58.27 |