| instruction-following-on-arena-hard-auto-v2 | LongCat-Flash | #1 | Accuracy: 86.50 |
| logic-puzzle-solving-on-zebralogic | LongCat-Flash | #1 | Accuracy: 89.30 |
| agents-on-bench-telecom | LongCat-Flash | #6 | Accuracy: 73.68 |
| multi-task-language-understanding-on-c-eval | LongCat-Flash | #8 | Accuracy: 90.44 |
| mathematical-reasoning-on-math-500 | LongCat-Flash | #18 | Accuracy: 96.40 |
| multi-task-language-understanding-on-mmlu-pro | LongCat-Flash | #30 | Accuracy: 82.68 |
| mathematical-reasoning-on-aime24 | LongCat-Flash | #47 | Acc: 70.42 |
| code-generation-on-livecodebench-v6 | LongCat-Flash | #53 | Pass@1: 48.02 |
| code-generation-on-swe-bench-verified | LongCat-Flash (OpenHands) | #64 | Accuracy: 60.40 |
| mathematical-reasoning-on-aime-2025 | LongCat-Flash | #67 | Accuracy: 61.25 |
| multiple-choice-question-answering-mcqa-on-gpqa-diamond | LongCat-Flash | #75 | Accuracy: 73.23 |