ResearchBenchmarksQuestion Answering on Science Q&A Biology (test)Follow55.9Mean@16SC-SDPO11.723.17534.6546.125May 26, 2026Evaluation ResultsMethodMethodLinksMean@16Majority@16SC-SDPOBackbone=OLMo-3-7B, Tr...Backbone=OLMo-3-7B, Training Method=SC-SDPO, Alpha (α)=0.5, Sampling Count (k)=162026.0555.958.2SDPOBackbone=OLMo-3-7B, Tr...Backbone=OLMo-3-7B, Training Method=SDPO, Sampling Count (k)=162026.055252OLMo-3-7BBackbone=OLMo-3-7B, Tr...Backbone=OLMo-3-7B, Training Method=Pre-trained, Sampling Count (k)=162026.0513.48