List your company

Medical Question Answering on SuperGPQA Clinical

35.71AccuracyIDC
25.122827.871430.6233.3686Mar 13, 2026

Evaluation results

MethodLinks
IDCBackbone=Llama-3.1-8B, Method Type=Iterative Distractor Curation2026.0335.71
DirectBackbone=Llama-3.1-8B, Method Type=Direct conversion to short-answer2026.0335.39
FilterBackbone=Llama-3.1-8B, Method Type=Filtering non-convertible questions2026.0335.39
RewriteBackbone=Llama-3.1-8B, Method Type=Model-based conversion2026.0335.39
Orig.Backbone=Llama-3.1-8B, Method Type=Standard RLVR on original MCQs2026.0333.58
BaseBackbone=Llama-3.1-8B, Method Type=Base instruct model2026.0333.25
IDCBackbone=Qwen2-7B, Method Type=Iterative Distractor Curation2026.0327.91
FilterBackbone=Qwen2-7B, Method Type=Filtering non-convertible questions2026.0326.6
RewriteBackbone=Qwen2-7B, Method Type=Model-based conversion2026.0326.27
DirectBackbone=Qwen2-7B, Method Type=Direct conversion to short-answer2026.0326.11
BaseBackbone=Qwen2-7B, Method Type=Base instruct model2026.0325.62
Orig.Backbone=Qwen2-7B, Method Type=Standard RLVR on original MCQs2026.0325.53