| multi-task-language-understanding-on-mmlu | I-DLM-32B | #2 | Average (%): 86.8 |
| code-generation-on-mbpp | I-DLM (32B) | #3 | Accuracy: 94.6 |
| mathematical-reasoning-on-math-500 | I-DLM (32B) | #8 | Accuracy: 97.6 |
| code-generation-on-humaneval | I-DLM-32B | #11 | Pass@1: 96.3 |
| mathematical-reasoning-on-aime24 | I-DLM (32B) | #22 | Acc: 83.3 |
| arithmetic-reasoning-on-gsm8k | I-DLM (8B) | #23 | Accuracy: 95.0 |
| mathematical-reasoning-on-aime-2025 | I-DLM (32B) | #40 | Accuracy: 80.0 |
| code-generation-on-livecodebench-v6 | I-DLM-32B | #44 | Pass@1: 57.1 |
| multi-task-language-understanding-on-mmlu-pro | I-DLM-32B | #45 | Accuracy: 79.7 |
| multiple-choice-question-answering-mcqa-on-gpqa-diamond | I-DLM (32B) | #93 | Accuracy: 62.1 |