Medical Reasoning on GPQA
51.8Accuracym1k
Evaluation results
| Method | Links | |
|---|---|---|
| m1kModel=Qwen2.5-7B-Instruct, Training=Finetuning, Sample size=1000 examples2026.06 | 51.8 | |
| Embedding DiversityModel=Qwen2.5-7B-Instruct, Training=Finetuning, Sample size=1000 examples2026.06 | 49.9 | |
| OursModel=Qwen2.5-7B-Instruct, Training=Finetuning, Sample size=1000 examples2026.06 | 49.6 | |
| Middle PerplexityModel=Qwen2.5-7B-Instruct, Training=Finetuning, Sample size=1000 examples2026.06 | 47.9 | |
| S2LModel=Qwen2.5-7B-Instruct, Training=Finetuning, Sample size=1000 examples2026.06 | 47.9 | |
| LearnabilityModel=Qwen2.5-7B-Instruct, Training=Finetuning, Sample size=1000 examples2026.06 | 47.3 | |
| RandomModel=Qwen2.5-7B-Instruct, Training=Finetuning, Sample size=1000 examples2026.06 | 46.9 |