| math-word-problem-solving-on-math | LLaDA2.0-flash | #1 | Accuracy: 95.44 |
| mathematical-reasoning-on-olympiadbench | LLaDA2.0-flash | #3 | Accuracy: 74.07 |
| mathematical-reasoning-on-omni-math | LLaDA2.0-flash | #3 | Accuracy: 50.3 |
| logic-puzzle-solving-on-zebralogic | LLaDA2.0-flash | #5 | Accuracy: 82.3 |
| code-generation-on-multipl-e | LLaDA2.0-flash | #6 | Accuracy: 74.87 |
| arithmetic-reasoning-on-gsm8k | LLaDA2.0-flash | #11 | Accuracy: 96.06 |
| code-generation-on-mbpp | LLaDA2.0-flash | #12 | Accuracy: 88.29 |
| code-generation-on-humaneval | LLaDA2.0-flash | #17 | Pass@1: 94.51 |
| multi-task-language-understanding-on-c-eval | LLaDA2.0-flash | #17 | Accuracy: 86.75 |
| sentence-completion-on-hellaswag | LLaDA2.0-flash | #39 | Accuracy: 84.97 |
| multi-task-language-understanding-on-mmlu-pro | LLaDA2.0-flash | #61 | Accuracy: 73.36 |
| mathematical-reasoning-on-aime-2025 | LLaDA2.0-flash | #71 | Accuracy: 60.0 |