ResearchBenchmarksMathematical Problem Solving on OlympiadFollow45Avg@32MASPO43.12843.61444.144.586Feb 19, 2026Evaluation ResultsMethodMethodLinksAvg@32Pass@32MASPOBackbone=DeepSeek-R1-D...Backbone=DeepSeek-R1-Distill-Qwen-14B2026.024553.7GRPOBackbone=DeepSeek-R1-D...Backbone=DeepSeek-R1-Distill-Qwen-14B2026.0243.250.7