Medical Question Answering on SuperGPQA Clinical
35.71AccuracyIDC
Evaluation Results
| Method | Links | |
|---|---|---|
| IDCBackbone=Llama-3.1-8B, Method Type=Iterative Distractor Curation2026.03 | 35.71 | |
| DirectBackbone=Llama-3.1-8B, Method Type=Direct conversion to short-answer2026.03 | 35.39 | |
| FilterBackbone=Llama-3.1-8B, Method Type=Filtering non-convertible questions2026.03 | 35.39 | |
| RewriteBackbone=Llama-3.1-8B, Method Type=Model-based conversion2026.03 | 35.39 | |
| Orig.Backbone=Llama-3.1-8B, Method Type=Standard RLVR on original MCQs2026.03 | 33.58 | |
| BaseBackbone=Llama-3.1-8B, Method Type=Base instruct model2026.03 | 33.25 | |
| IDCBackbone=Qwen2-7B, Method Type=Iterative Distractor Curation2026.03 | 27.91 | |
| FilterBackbone=Qwen2-7B, Method Type=Filtering non-convertible questions2026.03 | 26.6 | |
| RewriteBackbone=Qwen2-7B, Method Type=Model-based conversion2026.03 | 26.27 | |
| DirectBackbone=Qwen2-7B, Method Type=Direct conversion to short-answer2026.03 | 26.11 | |
| BaseBackbone=Qwen2-7B, Method Type=Base instruct model2026.03 | 25.62 | |
| Orig.Backbone=Qwen2-7B, Method Type=Standard RLVR on original MCQs2026.03 | 25.53 |