| code-generation-on-swe-bench-multilingual | LongCat-Flash-Lite (68.5B) | – | Accuracy: 38.1 |
| mathematical-reasoning-on-aime-2025 | LongCat-Flash-Lite (68.5B) | – | Accuracy: 63.23 |
| mathematical-reasoning-on-aime24 | LongCat-Flash-Lite (68.5B) | – | Acc: 72.19 |
| mathematical-reasoning-on-math-500 | LongCat-Flash-Lite (68.5B) | – | Accuracy: 96.8 |
| multi-task-language-understanding-on-c-eval | LongCat-Flash-Lite (68.5B) | – | Accuracy: 86.55 |
| multi-task-language-understanding-on-mmlu-pro | LongCat-Flash-Lite (68.5B) | – | Accuracy: 78.29 |
| multiple-choice-question-answering-mcqa-on-gpqa-diamond | LongCat-Flash-Lite (68.5B) | – | Accuracy: 66.78 |