| mathematical-reasoning-on-amo-bench | Falcon-H1R (7B) | #4 | Accuracy: 36.3 |
| mathematical-reasoning-on-aime-2025 | Falcon-H1R (7B) with DeepConf@512 | #5 | Accuracy: 96.7 |
| mathematical-reasoning-on-hmmt-feb-2025 | Falcon-H1R (7B) | #10 | Accuracy: 64.9 |
| mathematical-reasoning-on-math-500 | Falcon-H1R (7B) | #11 | Accuracy: 97.4 |
| mathematical-reasoning-on-aime24 | Falcon-H1R (7B) | #17 | Acc: 88.1 |
| code-generation-on-livecodebench-v6 | Falcon-H1R (7B) | #35 | Pass@1: 68.6 |
| instruction-following-on-ifbench | Falcon-H1R (7B) | #35 | Accuracy: 53.4 |
| question-answering-on-humanity-s-last-exam-hle | Falcon-H1R (7B) | #38 | Accuracy: 11.1 |