Clinical Diagnosis Identification on MIMIC Ext CDM IV
90.67Primary AccuracyDxChain
Evaluation Results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| DxChainBackbone=GPT-4.1-Mini2026.04 | 90.67 | 56.16 | 49.96 | 60.05 | 53.43 | |
| Base-model + CoTBackbone=GPT-4.1-Mini, Prompting Strategy=Chain-of-Thought2026.04 | 89.81 | 24.23 | 31.63 | 25.39 | 33.14 | |
| DxChainBackbone=GPT-5-Nano2026.04 | 89.65 | 47.86 | 48.33 | 46.97 | 47.43 | |
| KAMACBackbone=GPT-4.1-Mini2026.04 | 89.05 | 47.27 | 44.99 | 47.58 | 45.28 | |
| Base-modelBackbone=GPT-4.1-Mini2026.04 | 88.92 | 23.87 | 31.36 | 24.58 | 32.29 | |
| Base-modelBackbone=GPT-5-Nano2026.04 | 88.24 | 19.4 | 26.19 | 21.45 | 28.96 | |
| Base-model + CoTBackbone=GPT-5-Nano2026.04 | 87.68 | 19.76 | 26.68 | 21.53 | 29.08 | |
| DxChainBackbone=GPT-4.1-Mini2026.04 | 87.52 | — | — | — | — | |
| DxChainBackbone=GPT-5-Nano2026.04 | 87.48 | — | — | — | — | |
| KAMACBackbone=GPT-5-Nano2026.04 | 87.09 | 35.89 | 38.48 | 37.53 | 40.23 | |
| MAMBackbone=GPT-5-Nano2026.04 | 86.7 | 34.3 | 40.92 | 34.92 | 41.66 | |
| MedagentsBackbone=GPT-4.1-Mini2026.04 | 86.46 | 44.74 | 43.93 | 46.75 | 45.9 | |
| MedagentsBackbone=GPT-5-Nano2026.04 | 85.29 | 43.63 | 40.58 | 43.88 | 40.81 | |
| kamacBackbone=GPT-5-Nano2026.04 | 84.99 | — | — | — | — | |
| MAMBackbone=GPT-4.1-Mini2026.04 | 84.75 | 45.84 | 45.8 | 48.38 | 48.33 | |
| Base-model + CoTBackbone=GPT-4.1-Mini2026.04 | 83.95 | — | — | — | — | |
| Base-model + CoTBackbone=GPT-5-Nano2026.04 | 83.9 | — | — | — | — | |
| Base-modelBackbone=GPT-4.1-Mini2026.04 | 83.83 | — | — | — | — | |
| kamacBackbone=GPT-4.1-Mini2026.04 | 82.35 | — | — | — | — | |
| Base-modelBackbone=GPT-5-Nano2026.04 | 81.31 | — | — | — | — | |
| MedAgentsBackbone=GPT-4.1-Mini2026.04 | 80.59 | — | — | — | — | |
| MAMBackbone=GPT-5-Nano2026.04 | 79.47 | — | — | — | — | |
| MAMBackbone=GPT-4.1-Mini2026.04 | 79.03 | — | — | — | — | |
| MedAgentsBackbone=GPT-5-Nano2026.04 | 77.95 | — | — | — | — | |
| MDagentsBackbone=GPT-5-Nano2026.04 | 71.96 | 34.86 | 40.34 | 35.72 | 41.33 | |
| MDagentsBackbone=GPT-4.1-Mini2026.04 | 69.08 | 45.16 | 42.94 | 47.53 | 45.19 | |
| MDAgentsBackbone=GPT-5-Nano2026.04 | 61.4 | — | — | — | — | |
| MDAgentsBackbone=GPT-4.1-Mini2026.04 | 58.69 | — | — | — | — |