ResearchBenchmarksReasoning on Olympics-bench (Obly.)Follow58.5Avg@8 ScoreMT38.240843.500448.7654.0196Apr 22, 2026Evaluation ResultsMethodMethodLinksAvg@8 ScoreMTModel Family=Qwen 2.5,...Model Family=Qwen 2.5, Model Size=7B2026.0458.5HPDModel Family=Qwen 2.5,...Model Family=Qwen 2.5, Student Model=3B2026.0445.33HPDModel Family=LLaMA 3,...Model Family=LLaMA 3, Student Model=3B2026.0439.02