List your company

Mathematical Reasoning on AIME 25 (Peak avg@32 score)

30.31Peak avg@32 ScoreOTB
24.142825.743927.34528.9461Feb 6, 2026

Evaluation results

MethodLinks
OTBBackbone=Qwen3-8b-Base, Reasoning Paradigm=Single-Turn2026.0230.31
OGBBackbone=Qwen3-8b-Base, Reasoning Paradigm=Single-Turn2026.0230.1
OPOBackbone=Qwen3-8b-Base, Reasoning Paradigm=Single-Turn2026.0227.29
GRPOBackbone=Qwen3-8b-Base, Reasoning Paradigm=Single-Turn2026.0225.31
RLOOBackbone=Qwen3-8b-Base, Reasoning Paradigm=Single-Turn2026.0224.38