List your company

Single-Turn Mathematical Reasoning on AMC 23

85.08Peak avg@32 ScoreOTB
74.10876.956579.80582.6535Feb 6, 2026

Evaluation results

MethodLinks
OTBBackbone=Qwen3-8b-Base, Reasoning Paradigm=Single-Turn2026.0285.08
OPOBackbone=Qwen3-8b-Base, Reasoning Paradigm=Single-Turn2026.0284.53
GRPOBackbone=Qwen3-8b-Base, Reasoning Paradigm=Single-Turn2026.0280.86
OGBBackbone=Qwen3-8b-Base, Reasoning Paradigm=Single-Turn2026.0280.55
RLOOBackbone=Qwen3-8b-Base, Reasoning Paradigm=Single-Turn2026.0274.53