| instruction-following-on-mtbench | Qwen2.5-72B-Instruct | #1 | Score (1-10): 9.35 |
| multiple-choice-question-answering-mcqa-on-arc-challenge-25-shot | Qwen2.5-72B (25-shot) | #3 | Accuracy: 72.4 |
| reward-model-evaluation-on-rewardbench | Qwen2.5-RM-72B | #3 | Accuracy: 91.59 |
| question-answering-on-gpqa | Qwen2.5-72B-Instruct | #4 | Accuracy: 49 |
| code-generation-on-multipl-e | Qwen2.5-Plus | #5 | Accuracy: 77.0 |
| math-word-problem-solving-on-math | Qwen2.5-Plus | #11 | Accuracy: 84.7 |
| arithmetic-reasoning-on-gsm8k | Qwen2.5-Plus | #13 | Accuracy: 96.0 |
| code-generation-on-mbpp | Qwen2.5-72B-Instruct | #13 | Accuracy: 88.2 |
| multi-task-language-understanding-on-mmlu-redux | Qwen2.5-72B-Instruct | #21 | Accuracy: 86.8 |
| multi-task-language-understanding-on-mmlu-pro | Qwen2.5-Plus | #67 | Accuracy: 72.5 |
| multi-task-language-understanding-on-mmlu-pro | Qwen2.5-7B-Instruct | #105 | Accuracy: 56.3 |
| mathematical-reasoning-on-aime24 | Qwen2.5-72B-Instruct | #115 | Acc: 23.3 |
| code-generation-on-humaneval | Qwen2.5-Plus | – | Pass@1: 87.8 |