List your company

Mathematical Problem Solving on AIME24

54.1Pass@1Base Model
11.25222.37633.544.624Apr 20, 2026

Evaluation results

MethodLinks
Base ModelModel Scale=Qwen3-4B, Thinking Mode=Thinking2026.0454.175.5
MIXED-CUTSModel Scale=Qwen3-4B, Thinking Mode=Non-thinking2026.044673.5
GRPOModel Scale=Qwen3-4B, Thinking Mode=Non-thinking2026.0432.563.8
MIXED-CUTSModel Scale=Qwen3-1.7B, Thinking Mode=Non-thinking2026.0432.362
GRPOModel Scale=Qwen3-1.7B, Thinking Mode=Non-thinking2026.0429.560.7
Base ModelModel Scale=Qwen3-1.7B, Thinking Mode=Thinking2026.0428.962.8
Base ModelModel Scale=Qwen3-4B, Thinking Mode=Non-thinking2026.0424.254
Base ModelModel Scale=Qwen3-1.7B, Thinking Mode=Non-thinking2026.0412.936.5