List your company

Mathematical Reasoning on MATH 500 (EM, #Tool)

84.6EM (Accuracy)ParetoPO
65.25670.27875.380.322Jun 15, 2026

Evaluation results

MethodLinks
ParetoPOBase Model=Qwen2.5-Math-7B, Tool Use=Yes2026.0684.61.2
ToRL-GRPOBase Model=Qwen2.5-Math-7B, Tool Use=Yes2026.0682.22.2
OTC-GRPOBase Model=Qwen2.5-Math-7B, Tool Use=Yes2026.06811.5
MO-GRPOBase Model=Qwen2.5-Math-7B, Tool Use=Yes2026.0680.81.9
ParetoPOBase Model=Qwen2.5-Math-1.5B, Tool Use=Yes2026.06800.9
Qwen2.5-Math-7B-Ins-TIRBase Model=Qwen2.5-Math-7B, Tool Use=Yes2026.0678.81.6
ToRL-GRPOBase Model=Qwen2.5-Math-1.5B, Tool Use=Yes2026.0677.82.1
Qwen2.5-Math-7B-InsBase Model=Qwen2.5-Math-7B, Tool Use=No2026.0674.8—
OTC-GRPOBase Model=Qwen2.5-Math-1.5B, Tool Use=Yes2026.06741.3
Qwen2.5-Math-1.5B-Ins-TIRBase Model=Qwen2.5-Math-1.5B, Tool Use=Yes2026.0673.81.3
MO-GRPOBase Model=Qwen2.5-Math-1.5B, Tool Use=Yes2026.0671.22
Qwen2.5-Math-1.5B-InsBase Model=Qwen2.5-Math-1.5B, Tool Use=No2026.0666—