List your company

Mathematical Problem Solving on AIME 25 (Pass@1, Pass@16)

42.1Pass@1Base Model
10.48418.69226.935.108Apr 20, 2026

Evaluation results

MethodLinks
Base ModelModel Scale=Qwen3-4B, Thinking Mode=Thinking2026.0442.162.3
MIXED-CUTSModel Scale=Qwen3-4B, Thinking Mode=Non-thinking2026.0441.771.9
MIXED-CUTSModel Scale=Qwen3-1.7B, Thinking Mode=Non-thinking2026.0428.152.5
GRPOModel Scale=Qwen3-4B, Thinking Mode=Non-thinking2026.0426.657.9
Base ModelModel Scale=Qwen3-1.7B, Thinking Mode=Thinking2026.0424.944.5
GRPOModel Scale=Qwen3-1.7B, Thinking Mode=Non-thinking2026.0422.844.5
Base ModelModel Scale=Qwen3-4B, Thinking Mode=Non-thinking2026.0421.548
Base ModelModel Scale=Qwen3-1.7B, Thinking Mode=Non-thinking2026.0411.727.8