Medical Reasoning on Medical task
43.7AccuracySDFT
Evaluation results
| Method | Links | ||
|---|---|---|---|
| SDFTBase Model=Olmo-3-7B-Think, Fine-tuning strategy=Self-Distillation Fine-Tuning2026.01 | 43.7 | 4,180 | |
| Olmo-3-7B-ThinkFine-tuning strategy=Base Model2026.01 | 31.2 | 4,612 | |
| SFTBase Model=Olmo-3-7B-Think, Fine-tuning strategy=Supervised Fine-Tuning2026.01 | 23.5 | 3,273 |