| mathematical-reasoning-on-math-500 | SR 2 AM-v1.0-30B | #1 | Accuracy: 99.2 |
| multiple-choice-question-answering-mcqa-on-supergpqa | SR 2 AM-v1.0-30B | #1 | Accuracy: 73.0 |
| mathematical-reasoning-on-aime24 | SR 2 AM-v1.0-30B | #2 | Acc: 96.2 |
| question-answering-on-humanity-s-last-exam-hle | SR 2 AM-v1.0-30B | #11 | Accuracy: 30.4 |
| mathematical-reasoning-on-aime-2025 | SR 2 AM-v1.0-30B | #18 | Accuracy: 91.1 |
| deep-research-agents-on-browsecomp | SR 2 AM-v1.0-30B | #60 | Accuracy: 22.5 |
| multiple-choice-question-answering-mcqa-on-gpqa-diamond | SR 2 AM-v1.0-30B | #61 | Accuracy: 77.3 |