Multi-task evaluation on Aggregated Clinical Tasks
74.6Average ScoreFull FT
Evaluation Results
| Method | Links | |
|---|---|---|
| Full FTBase model=gpt-oss 20B, Trainable Parameters=100.0%2026.04 | 74.6 | |
| MPTBase model=gpt-oss 20B, Trainable Parameters=<0.05%2026.04 | 73.9 | |
| LoRABase model=gpt-oss 20B, Trainable Parameters=~2.50%2026.04 | 72.4 | |
| Full FTBase model=Meditron3 8B, Trainable Parameters=100.0%2026.04 | 72.2 | |
| MPTBase model=Meditron3 8B, Trainable Parameters=<0.05%2026.04 | 71.5 | |
| Full FTBase model=LLaMA 3.1 8B, Trainable Parameters=100.0%2026.04 | 69.9 | |
| LoRABase model=Meditron3 8B, Trainable Parameters=~2.50%2026.04 | 69.9 | |
| MPTBase model=LLaMA 3.1 8B, Trainable Parameters=<0.05%2026.04 | 69.1 | |
| PTBase model=gpt-oss 20B, Trainable Parameters=<0.05%2026.04 | 67.9 | |
| LoRABase model=LLaMA 3.1 8B, Trainable Parameters=~2.50%2026.04 | 67.4 | |
| PTBase model=Meditron3 8B, Trainable Parameters=<0.05%2026.04 | 65.1 | |
| PTBase model=LLaMA 3.1 8B, Trainable Parameters=<0.05%2026.04 | 62.5 |