Medical Reasoning on Medical-O1-Reasoning-SFT
1WinsLLM-AutoDP
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| LLM-AutoDPBackbone=Gemma-2-9B, Baseline Comparison=No-Process2026.01 | 1 | 0 | 0 | |
| LLM-AutoDPBackbone=Gemma-2-9B, Baseline Comparison=SELA2026.01 | 0.5339 | 0.0738 | 0.3923 | |
| LLM-AutoDPBackbone=Gemma-2-9B, Baseline Comparison=RS2026.01 | 0.5252 | 0.0749 | 0.3999 | |
| LLM-AutoDPBackbone=Llama3.1-8B, Baseline Comparison=RS2026.01 | 0.5111 | 0.0833 | 0.4056 | |
| LLM-AutoDPBackbone=Qwen2.5-7B, Baseline Comparison=RS2026.01 | 0.4969 | 0.0925 | 0.4106 | |
| LLM-AutoDPBackbone=Gemma-2-9B, Baseline Comparison=All-Process2026.01 | 0.4766 | 0.0919 | 0.4315 | |
| LLM-AutoDPBackbone=Qwen2.5-7B, Baseline Comparison=SELA2026.01 | 0.4748 | 0.0933 | 0.4319 | |
| LLM-AutoDPBackbone=Qwen2.5-7B, Baseline Comparison=All-Process2026.01 | 0.4724 | 0.0944 | 0.4332 | |
| LLM-AutoDPBackbone=Llama3.1-8B, Baseline Comparison=SELA2026.01 | 0.4698 | 0.0969 | 0.4333 | |
| LLM-AutoDPBackbone=Llama3.1-8B, Baseline Comparison=All-Process2026.01 | 0.4538 | 0.0713 | 0.4749 | |
| LLM-AutoDPBackbone=Qwen2.5-7B, Baseline Comparison=No-Process2026.01 | 0 | 1 | 0 | |
| LLM-AutoDPBackbone=Llama3.1-8B, Baseline Comparison=No-Process2026.01 | 0 | 1 | 0 |