List your company

Mathematical Reasoning on MATH500 (P@1 and TTFR)

85.2P@1Plan-Answer
81.45682.42883.484.372Dec 2, 2025

Evaluation results

MethodLinks
Plan-AnswerModel=Qwen3-8B, Decoding Strategy=Plan-Answer2025.1285.2625
Plan-AnswerModel=Qwen3-4B, Decoding Strategy=Plan-Answer2025.1284.4628
Think-AnswerModel=Qwen3-8B, Decoding Strategy=Think-Answer2025.12831,587
Think-AnswerModel=Qwen3-4B, Decoding Strategy=Think-Answer2025.1282.81,492
No ThinkingModel=Qwen3-8B, Decoding Strategy=No Thinking2025.1282.40
No ThinkingModel=Qwen3-4B, Decoding Strategy=No Thinking2025.1281.60