ResearchBenchmarksQuestion Answering on Science Q&A Physics (test)Follow71.1Mean@16SC-SDPO31.78841.99452.262.406May 26, 2026Evaluation ResultsMethodMethodLinksMean@16Majority Voting@16SC-SDPOBackbone=OLMo-3-7B, Tr...Backbone=OLMo-3-7B, Training Method=SC-SDPO, Alpha (α)=0.5, Sampling Count (k)=162026.0571.173.4SDPOBackbone=OLMo-3-7B, Tr...Backbone=OLMo-3-7B, Training Method=SDPO, Sampling Count (k)=162026.0568.268.7OLMo-3-7BBackbone=OLMo-3-7B, Tr...Backbone=OLMo-3-7B, Training Method=Pre-trained, Sampling Count (k)=162026.0533.330