| mathematical-reasoning-on-aime-2025 | RISE (logit,Qwen3-8B,beta0=1.5) | – | Accuracy: 47.9 |
| mathematical-reasoning-on-aime24 | RISE (logit,Qwen3-8B,cosineschedule) | – | Acc: 58.5 |
| mathematical-reasoning-on-math-500 | RISE (weight,Qwen3-8B,3-seedmean) | – | Accuracy: 84.9 |
| mathematical-reasoning-on-minerva-math | RISE (weight,Qwen3-8B) | – | Accuracy: 32.6 |
| mathematical-reasoning-on-olympiadbench | RISE (weight,Qwen3-8B,3-seedmean) | – | Accuracy: 64.4 |
| multi-task-language-understanding-on-mmlu-pro | RISE (logit,Qwen3-8B) | – | Accuracy: 74.3 |
| multiple-choice-question-answering-mcqa-on-gpqa-diamond | RISE (weight,Qwen3-8B) | – | Accuracy: 59.0 |