Clinical quality indicator checking on CMQCIC-Bench v1 (test)
95.54AccuracyQwen2.5-72B
Evaluation results
| Method | Links | |
|---|---|---|
| Qwen2.5-72BShots=1, Strategy=CF-IR2025.02 | 95.54 | |
| HumanNote=Baseline performance2025.02 | 95 | |
| Qwen2.5-32BShots=1, Strategy=CF-IR2025.02 | 94.77 | |
| GPT-4oShots=1, Strategy=CF-IR2025.02 | 93.88 | |
| Qwen2.5-72BShots=0, Strategy=CF-IR2025.02 | 92.73 | |
| Qwen2.5-32BShots=1, Strategy=ACF-IR2025.02 | 92.35 | |
| llama3.1-70BShots=1, Strategy=CF-IR2025.02 | 91.84 | |
| GPT-4oShots=0, Strategy=CF-IR2025.02 | 91.84 | |
| Qwen2.5-14BShots=1, Strategy=CF-IR2025.02 | 91.59 | |
| GPT-4oShots=1, Strategy=CoT2025.02 | 91.59 | |
| Qwen2.5-72BShots=1, Strategy=ACF-IR2025.02 | 91.33 | |
| Qwen2.5-72BShots=1, Strategy=CoT2025.02 | 90.95 | |
| GPT-4oShots=1, Strategy=ACF-IR2025.02 | 90.57 | |
| Qwen2.5-7BShots=1, Strategy=CF-IR2025.02 | 89.93 | |
| Qwen2.5-32BShots=1, Strategy=CoT2025.02 | 89.8 | |
| GPT-4oShots=0, Strategy=CoT2025.02 | 88.91 | |
| Internlm2.5-20BShots=1, Strategy=CF-IR2025.02 | 88.78 | |
| llama3.1-70BShots=1, Strategy=CoT2025.02 | 88.53 | |
| Qwen2.5-14BShots=1, Strategy=CoT2025.02 | 87.89 | |
| Qwen2.5-72BShots=0, Strategy=Standard2025.02 | 87.77 | |
| Qwen2.5-72BShots=0, Strategy=CoT2025.02 | 87.51 | |
| Qwen2.5-32BShots=0, Strategy=CF-IR2025.02 | 87.21 | |
| Qwen2.5-32BShots=0, Strategy=CoT2025.02 | 86.49 | |
| Internlm2.5-20BShots=1, Strategy=CoT2025.02 | 86.36 | |
| Apollo-72BShots=1, Strategy=CF-IR2025.02 | 86.36 | |
| Qwen2.5-14BShots=0, Strategy=CF-IR2025.02 | 86.11 | |
| Apollo-72BShots=1, Strategy=CoT2025.02 | 86.11 | |
| llama3.1-8BShots=1, Strategy=CF-IR2025.02 | 85.85 | |
| llama3.1-70BShots=0, Strategy=CoT2025.02 | 85.85 | |
| Qwen2.5-7BShots=1, Strategy=ACF-IR2025.02 | 85.73 | |
| llama3.1-70BShots=0, Strategy=CF-IR2025.02 | 85.47 | |
| Qwen2.5-7BShots=1, Strategy=CoT2025.02 | 85.22 | |
| Qwen2.5-14BShots=1, Strategy=ACF-IR2025.02 | 84.96 | |
| Internlm2.5-7BShots=1, Strategy=CF-IR2025.02 | 84.45 | |
| llama3.1-70BShots=1, Strategy=ACF-IR2025.02 | 84.45 | |
| Internlm2.5-7BShots=1, Strategy=CoT2025.02 | 84.07 | |
| MiniCPM3-4BShots=1, Strategy=CoT2025.02 | 83.56 | |
| Internlm2.5-20BShots=1, Strategy=ACF-IR2025.02 | 83.06 | |
| Qwen2.5-7BShots=0, Strategy=CF-IR2025.02 | 82.92 | |
| Qwen2.5-7BShots=0, Strategy=CoT2025.02 | 82.8 | |
| MiniCPM3-4BShots=1, Strategy=CF-IR2025.02 | 82.67 | |
| llama3.1-70BShots=0, Strategy=Standard2025.02 | 82.54 | |
| Qwen2.5-3BShots=1, Strategy=CF-IR2025.02 | 82.03 | |
| Qwen2.5-14BShots=0, Strategy=CoT2025.02 | 82.03 | |
| llama3.1-8BShots=1, Strategy=CoT2025.02 | 81.52 | |
| Internlm2.5-20BShots=0, Strategy=CF-IR2025.02 | 80.63 | |
| Apollo-72BShots=1, Strategy=ACF-IR2025.02 | 80.63 | |
| Internlm2.5-7BShots=0, Strategy=CF-IR2025.02 | 79.49 | |
| Qwen2.5-3BShots=1, Strategy=ACF-IR2025.02 | 79.36 | |
| MiniCPM3-4BShots=1, Strategy=ACF-IR2025.02 | 78.98 | |
| Qwen2.5-14BShots=0, Strategy=Standard2025.02 | 78.98 | |
| llama3.1-8BShots=0, Strategy=CF-IR2025.02 | 78.34 | |
| Qwen2.5-3BShots=1, Strategy=CoT2025.02 | 77.83 | |
| Internlm2.5-20BShots=0, Strategy=CoT2025.02 | 77.57 | |
| GPT-4oShots=0, Strategy=Standard2025.02 | 77.45 | |
| Internlm2.5-7BShots=1, Strategy=ACF-IR2025.02 | 77.07 | |
| Apollo-72BShots=0, Strategy=CoT2025.02 | 76.24 | |
| Qwen2.5-32BShots=0, Strategy=Standard2025.02 | 75.54 | |
| llama3.1-8BShots=1, Strategy=ACF-IR2025.02 | 73.88 | |
| Qwen2.5-3BShots=0, Strategy=CoT2025.02 | 73.37 | |
| Qwen2.5-1.5BShots=1, Strategy=CF-IR2025.02 | 73.24 | |
| Internlm2.5-7BShots=0, Strategy=CoT2025.02 | 73.12 | |
| Apollo-72BShots=0, Strategy=CF-IR2025.02 | 72.61 | |
| MiniCPM3-4BShots=0, Strategy=CoT2025.02 | 72.1 | |
| Apollo2-7BShots=1, Strategy=CoT2025.02 | 71.71 | |
| Qwen2.5-1.5BShots=1, Strategy=CoT2025.02 | 71.21 | |
| Internlm2.5-20BShots=0, Strategy=Standard2025.02 | 69.04 | |
| MiniCPM3-4BShots=0, Strategy=CF-IR2025.02 | 68.91 | |
| Internlm2.5-1.8BShots=1, Strategy=CoT2025.02 | 68.91 | |
| Apollo-72BShots=0, Strategy=Standard2025.02 | 68.91 | |
| Qwen2.5-3BShots=0, Strategy=CF-IR2025.02 | 67.64 | |
| Qwen2.5-7BShots=0, Strategy=Standard2025.02 | 66.49 | |
| Qwen2.5-1.5BShots=0, Strategy=Standard2025.02 | 66.11 | |
| Apollo2-1.5BShots=1, Strategy=CoT2025.02 | 66.11 | |
| Internlm2.5-1.8BShots=1, Strategy=ACF-IR2025.02 | 65.85 | |
| Apollo2-0.5BShots=1, Strategy=CF-IR2025.02 | 65.47 | |
| Apollo2-7BShots=1, Strategy=CF-IR2025.02 | 65.35 | |
| Apollo2-1.5BShots=1, Strategy=CF-IR2025.02 | 65.22 | |
| Internlm2.5-1.8BShots=1, Strategy=CF-IR2025.02 | 64.07 | |
| Qwen2.5-1.5BShots=0, Strategy=CoT2025.02 | 63.43 | |
| MiniCPM3-4BShots=0, Strategy=Standard2025.02 | 63.31 | |
| Internlm2.5-7BShots=0, Strategy=Standard2025.02 | 63.31 | |
| llama3.1-8BShots=0, Strategy=CoT2025.02 | 63.05 | |
| Qwen2.5-1.5BShots=0, Strategy=CF-IR2025.02 | 62.42 | |
| Apollo2-7BShots=0, Strategy=CF-IR2025.02 | 61.91 | |
| Qwen2.5-0.5BShots=1, Strategy=CoT2025.02 | 61.01 | |
| Qwen2.5-1.5BShots=1, Strategy=ACF-IR2025.02 | 60.5 | |
| Qwen2.5-3BShots=0, Strategy=Standard2025.02 | 60.38 | |
| Apollo2-7BShots=0, Strategy=CoT2025.02 | 60 | |
| Apollo2-7BShots=0, Strategy=Standard2025.02 | 57.57 | |
| Apollo2-0.5BShots=1, Strategy=ACF-IR2025.02 | 57.19 | |
| HuatuoGPT2-7BShots=1, Strategy=CF-IR2025.02 | 56.81 | |
| Internlm2.5-1.8BShots=0, Strategy=CoT2025.02 | 56.18 | |
| Internlm2.5-1.8BShots=0, Strategy=Standard2025.02 | 56.17 | |
| Qwen2.5-0.5BShots=0, Strategy=CoT2025.02 | 56.05 | |
| HuatuoGPT2-14BShots=0, Strategy=CoT2025.02 | 55.28 | |
| Apollo2-0.5BShots=1, Strategy=CoT2025.02 | 54.39 | |
| Qwen2.5-0.5BShots=0, Strategy=Standard2025.02 | 54.26 | |
| HuatuoGPT2-7BShots=0, Strategy=CoT2025.02 | 54.26 | |
| Internlm2.5-1.8BShots=0, Strategy=CF-IR2025.02 | 54.14 |