| zero-shot-question-answering-on-truthfulqa-mc2-0-shot | Qwen2-57B-A14B | #1 | MC2Acc: 57.7 |
| zero-shot-question-answering-on-truthfulqa-mc2-0-shot | Qwen2-72B | #2 | MC2Acc: 54.8 |
| instruction-following-on-alignbench | Qwen2-72B-Instruct | #3 | Score (0-10): 8.27 |
| instruction-following-on-alignbench | Qwen2-57B-A14B-Instruct | #6 | Score (0-10): 7.36 |
| instruction-following-on-mtbench | Qwen2-72B-Instruct | #3 | Score (1-10): 9.12 |
| instruction-following-on-mtbench | Qwen2-57B-A14B-Instruct | #7 | Score (1-10): 8.55 |
| multiple-choice-question-answering-mcqa-on-arc-challenge-25-shot | Qwen2-72B | #4 | Accuracy: 68.9 |
| multiple-choice-question-answering-mcqa-on-arc-challenge-25-shot | Qwen2-57B-A14B | #8 | Accuracy: 64.1 |
| arithmetic-reasoning-on-gsm8k | Qwen2-Math-72B-Instruct
(greedy) | #7 | Accuracy: 96.7Parameters (Billion): 72 |
| instruction-following-on-ifeval | Qwen2-72B-Instruct | #8 | Prompt-level strict-accuracy: 77.6 |
| instruction-following-on-ifeval | Qwen2-57B-A14B-Instruct | #9 | Prompt-level strict-accuracy: 59.9 |
| multi-task-language-understanding-on-mmlu | Qwen2-72B | #8 | Average (%): 84.2 |
| multi-task-language-understanding-on-mmlu | Qwen2-72B-Instruct | #11 | Average (%): 82.3 |
| multi-task-language-understanding-on-mmlu | Qwen2-57B-A14B | #16 | Average (%): 76.5 |
| multi-task-language-understanding-on-mmlu | Qwen2-57B-A14B-Instruct | #17 | Average (%): 75.4 |
| code-generation-on-multipl-e | Qwen2-72B-Instruct | #9 | Accuracy: 69.2 |
| code-generation-on-multipl-e | Qwen2-57B-A14B-Instruct | #10 | Accuracy: 66.4 |
| code-generation-on-multipl-e | Qwen2-72B | #13 | Accuracy: 59.6 |
| code-generation-on-multipl-e | Qwen2-57B-A14B | #15 | Accuracy: 49.8 |
| math-word-problem-solving-on-math | Qwen2-Math-72B-Instruct(greedy) | #13 | Accuracy: 84.0Parameters (Billions): 72 |
| common-sense-reasoning-on-winogrande | Qwen2-72B | #14 | Accuracy: 85.1 |
| common-sense-reasoning-on-winogrande | Qwen2-57B-A14B | #33 | Accuracy: 79.5 |
| sentence-completion-on-hellaswag | Qwen2-72B | #23 | Accuracy: 87.6 |
| sentence-completion-on-hellaswag | Qwen2-57B-A14B | #38 | Accuracy: 85.2 |
| code-generation-on-mbpp | Qwen2-72B-Instruct | #33 | Accuracy: 80.2 |
| code-generation-on-mbpp | Qwen2-72B | #39 | Accuracy: 76.9 |
| code-generation-on-mbpp | Qwen2-57B-A14B | #52 | Accuracy: 71.9 |
| code-generation-on-mbpp | Qwen2-57B-A14B-Instruct | #53 | Accuracy: 70.9 |
| code-generation-on-humaneval | Qwen2-72B-Instruct | #44 | Pass@1: 86.0 |
| code-generation-on-humaneval | Qwen2-57B-A14B-Instruct | #58 | Pass@1: 79.9 |
| multi-task-language-understanding-on-mmlu-pro | Qwen2-72B-Instruct | #82 | Accuracy: 64.4 |
| multi-task-language-understanding-on-mmlu-pro | Qwen2-72B | #105 | Accuracy: 55.6 |
| multi-task-language-understanding-on-mmlu-pro | Qwen2-57B-A14B-Instruct | #109 | Accuracy: 52.8 |