Diagnostic Precision on ClinicalBench (test)
76.9AccuracyMedCollab
Evaluation Results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| MedCollab2026.03 | 76.9 | 72.4 | 36.7 | 94.3 | 100 | |
| ClinicalAgentCategory=Multi-Agents2026.03 | 68.7 | 51.3 | 25.6 | 75.6 | 100 | |
| GLM-4.7Category=Leading LLMs2026.03 | 66.9 | 59.3 | 30.5 | 88.5 | 100 | |
| Qwen3-MaxCategory=Leading LLMs2026.03 | 66.9 | 56.7 | 27.8 | 84.5 | 100 | |
| Gemini-3-FlashCategory=Leading LLMs2026.03 | 66.1 | 57 | 37.2 | 87.6 | 100 | |
| GPT-4oCategory=Leading LLMs2026.03 | 65.5 | 56.5 | 32.3 | 86.2 | 100 | |
| MedLACategory=Multi-Agents2026.03 | 63.4 | 54.3 | 32.1 | 85.7 | 99.9 | |
| Baichuan4-TurboCategory=Leading LLMs2026.03 | 53.9 | 41.3 | 35.1 | 77.4 | 98 | |
| Qwen3-8BCategory=Leading LLMs2026.03 | 52.9 | 39.6 | 31.8 | 72.6 | 97.6 | |
| HuatuoGPT-o1-8BCategory=Leading LLMs2026.03 | 42.9 | 32.7 | 29.1 | 76.7 | 80.8 | |
| MEDDxAgentCategory=Multi-Agents2026.03 | 36.9 | — | 26.8 | — | — |