List your company

Mathematical Reasoning on AMC (Pass@16, Mean@16, Token Usage)

47.06Mean @16ME-ICPO
-0.634411.747824.1336.5122Dec 2, 2025Dec 17, 2025Jan 1, 2026Jan 16, 2026Jan 31, 2026Feb 15, 2026Mar 2, 2026

Evaluation results

MethodLinks
ME-ICPOBackbone=Qwen2.5-Math-7B, Time(s/question)=11522026.0347.06————
TTRLBackbone=Qwen2.5-Math-7B, Time(s/question)=12532026.0345.18————
OptPO-SFTBackbone=Qwen2.5-Math-1.5B2025.1239.781.943.4—12.08
TTSFTBackbone=Qwen2.5-Math-1.5B2025.1237.980.742.2——
ToT (Maj vote)Backbone=Qwen2.5-Math-7B, Time(s/question)=3632026.0329.37————
TTSFTBackbone=Llama-3.1-8B-Instruct2025.1220.163.928.9——
OptPO-SFTBackbone=Llama-3.1-8B-Instruct2025.1218.760.219.3—17.16
ToT (self eval)Backbone=Qwen2.5-Math-7B, Time(s/question)=7082026.0316.19————
MCTRBackbone=Qwen2.5-Math-7B, Time(s/question)=17582026.031.2————