Rare disease diagnosis from phenotypes on RareBench-Public Phenotypes
37.92AccuracyDeepSeek-R1-671B
Evaluation Results
| Method | Links | |
|---|---|---|
| DeepSeek-R1-671BZero-shot=true, Category=Large-scale LLMs (Open-domain)2026.06 | 37.92 | |
| RareDxR1-D-14BZero-shot=true, Category=Comparable-sized LLMs (Open-domain)2026.06 | 37 | |
| Gemini-2.5-FlashZero-shot=true, Category=Large-scale LLMs (Open-domain)2026.06 | 35.51 | |
| Doubao-1.5-Thinking-ProZero-shot=true, Category=Large-scale LLMs (Open-domain)2026.06 | 31.96 | |
| DeepSeek-Distill-14BZero-shot=true, Category=Comparable-sized LLMs (Open-domain)2026.06 | 30.93 | |
| PhenoBrainZero-shot=true, Category=Specialized Method (Closed-set)2026.06 | 30.4 | |
| GPT-4oZero-shot=true, Category=Large-scale LLMs (Open-domain)2026.06 | 30.01 | |
| Baichuan-M1-14BZero-shot=true, Category=Comparable-sized LLMs (Open-domain)2026.06 | 30.01 | |
| HuatuoGPT-o1-70BZero-shot=true, Category=Comparable-sized LLMs (Open-domain)2026.06 | 29.44 |