List your company

Mathematical Reasoning on AIME 25 (Pass@1, Pass@8, #Invoc.)

0.6556Pass@1DART
0.1138640.2545070.395150.535793Jan 13, 2026

Evaluation results

MethodLinks
DARTBackbone=Qwen3-4B-Thinking-2507, Paradigm=RL, CoT Type=tool-integrated long2026.010.65560.85769.51
UTIRBackbone=Qwen3-4B-Thinking-2507, Paradigm=RL, CoT Type=tool-integrated long2026.010.63890.77968.12
DAPOBackbone=Qwen3-4B-Thinking-2507, Paradigm=RL, CoT Type=pure-text long2026.010.61530.84090
ToRL-ThinkBackbone=Qwen3-4B-Thinking-2507, Paradigm=RL, CoT Type=pure-text long2026.010.61250.76270
UTIRBackbone=Qwen3-8B, Paradigm=RL, CoT Type=tool-integrated long2026.010.61110.749610.22
ToRL-ThinkBackbone=Qwen3-8B, Paradigm=RL, CoT Type=pure-text long2026.010.59440.69910
DARTBackbone=Qwen3-8B, Paradigm=RL, CoT Type=tool-integrated long2026.010.57640.790210.66
DAPOBackbone=Qwen3-8B, Paradigm=RL, CoT Type=pure-text long2026.010.56110.76980
Original checkpointBackbone=Qwen3-8B, CoT Type=pure-text long2026.010.52080.69220
Original checkpointBackbone=Qwen3-4B-Thinking-2507, CoT Type=pure-text long2026.010.46390.650
STARTBackbone=Qwen3-4B-Thinking-2507, Paradigm=SFT, CoT Type=tool-integrated long2026.010.38470.58912.08
ToRL-BaseBackbone=Qwen3-4B-Thinking-2507, Paradigm=RL, CoT Type=tool-integrated short2026.010.31810.42242.99
STARTBackbone=Qwen3-8B, Paradigm=SFT, CoT Type=tool-integrated long2026.010.30280.497612.77
RetoolBackbone=Qwen3-8B, Paradigm=SFT+RL, CoT Type=tool-integrated short2026.010.30.43511.2
ToRL-BaseBackbone=Qwen3-8B, Paradigm=RL, CoT Type=tool-integrated short2026.010.25830.37282.98
RetoolBackbone=Qwen3-4B-Thinking-2507, Paradigm=SFT+RL, CoT Type=tool-integrated short2026.010.20130.36361.35
Retool (only SFT)Backbone=Qwen3-8B, Paradigm=SFT, CoT Type=tool-integrated short2026.010.19670.31182.07
Retool (only SFT)Backbone=Qwen3-4B-Thinking-2507, Paradigm=SFT, CoT Type=tool-integrated short2026.010.13470.23421.89