Disease Diagnosis on MIMIC-IV-Ext Cardiac Disease (test)
75.04Primary Diagnosis AccuracyDxChain
Evaluation Results
| Method | Links | |
|---|---|---|
| DxChainBackbone=GPT-4.1-Mini2026.04 | 75.04 | |
| kamacBackbone=GPT-5-Nano2026.04 | 70.35 | |
| DxChainBackbone=GPT-5-Nano2026.04 | 69.83 | |
| Base-modelBackbone=GPT-5-Nano2026.04 | 67.77 | |
| Base-model + CoTBackbone=GPT-5-Nano2026.04 | 66.26 | |
| MAMBackbone=GPT-5-Nano2026.04 | 64.91 | |
| Base-modelBackbone=GPT-4.1-Mini2026.04 | 64.78 | |
| kamacBackbone=GPT-4.1-Mini2026.04 | 64.69 | |
| Base-model + CoTBackbone=GPT-4.1-Mini2026.04 | 64.06 | |
| MAMBackbone=GPT-4.1-Mini2026.04 | 63.57 | |
| MedAgentsBackbone=GPT-4.1-Mini2026.04 | 63.09 | |
| MDAgentsBackbone=GPT-4.1-Mini2026.04 | 62.16 | |
| MDAgentsBackbone=GPT-5-Nano2026.04 | 60.58 | |
| MedAgentsBackbone=GPT-5-Nano2026.04 | 57.54 |