Consultation Capability Evaluation on ClinicalBench
4.04Conversation ArrangementMiniMax-M2
Evaluation Results
| Method | Links | |||||||
|---|---|---|---|---|---|---|---|---|
| MiniMax-M2Open-source=true2026.04 | 4.04 | 4.77 | 4.77 | 4.44 | 4.99 | 4.85 | 9.14 | |
| Kimi K2 ThinkingOpen-source=true2026.04 | 4.02 | 4.88 | 4.93 | 4.58 | 4.99 | 4.97 | 8.96 | |
| AegleBase Model=DeepSeek-V3.22026.04 | 4.02 | 4.95 | 4.94 | 4.21 | 5 | 5 | 10.16 | |
| HuatuoGPT-o1-7BOpen-source=true, Medical-domain=true2026.04 | 4.01 | 4.44 | 4.88 | 4.15 | 4.96 | 4.92 | 21.67 | |
| DeepSeek-V3.2Open-source=true2026.04 | 4.01 | 4.55 | 4.81 | 4.31 | 4.93 | 4.86 | 20.5 | |
| Qwen3-MaxProprietary=true2026.04 | 4.01 | 4.9 | 4.96 | 4.38 | 5 | 4.96 | 6.42 | |
| Qwen3-8B-thinkOpen-source=true2026.04 | 4 | 4.1 | 4.69 | 4.78 | 4.94 | 4.14 | 7.03 | |
| Lingshu-32BOpen-source=true, Medical-domain=true2026.04 | 4 | 4.52 | 4.91 | 4.34 | 4.98 | 4.91 | 8.03 | |
| DeepSeek-V3.2-ThinkingOpen-source=true2026.04 | 4 | 4.86 | 4.96 | 4.57 | 4.99 | 4.97 | 8.8 | |
| GLM-4.6Open-source=true2026.04 | 4 | 4.65 | 4.97 | 4.79 | 5 | 4.98 | 8.21 | |
| GPT-4oProprietary=true2026.04 | 4 | 4.74 | 4.93 | 4.91 | 5 | 4.56 | 4.6 | |
| Doubao-Seed-1.6Proprietary=true2026.04 | 4 | 4.45 | 4.88 | 4.61 | 4.99 | 4.66 | 10.43 | |
| ERNIE-5.0-PreviewProprietary=true2026.04 | 4 | 4.55 | 4.92 | 4.59 | 4.97 | 4.39 | 5.06 | |
| CoTBase Model=DeepSeek-V3.22026.04 | 4 | 4.83 | 4.63 | 4.05 | 4.99 | 4.85 | 6.4 | |
| ToTBase Model=DeepSeek-V3.22026.04 | 4 | 4.86 | 4.65 | 4 | 4.99 | 4.89 | 7.37 | |
| MDAgentsBase Model=DeepSeek-V3.22026.04 | 4 | 4.66 | 4.85 | 4.32 | 4.98 | 4.93 | 6.59 | |
| MedAgentsBase Model=DeepSeek-V3.22026.04 | 4 | 4.58 | 4.9 | 4.55 | 5 | 4.8 | 6.96 | |
| Baichuan-M2-32BOpen-source=true, Medical-domain=true2026.04 | 3.99 | 3.97 | 4.47 | 4.86 | 4.89 | 3.97 | 11.54 | |
| Gemini 2.5Proprietary=true2026.04 | 3.88 | 3.58 | 4.12 | 4.89 | 4.38 | 4 | 29.98 |