List your company

Mathematical Reasoning on Math-CoT-20K

77.1AIME24 AccuracyOPSD-PMI
50.99657.77364.5571.327Jul 2, 2026

Evaluation results

MethodLinks
OPSD-PMIModel=Qwen3-8B2026.0777.170.847.565.1
OPSD-PMIModel=Qwen3-4B2026.0776.167.544.462.7
BaseModel=Qwen3-8B2026.0775.865.643.961.8
OPSD-StandardModel=Qwen3-8B2026.0775.866.744.462.3
BaseModel=Qwen3-4B2026.0774.966.442.261.2
OPSD-StandardModel=Qwen3-4B2026.0773.364.240.859.4
OPSD-PMIModel=OLMo-7B2026.0773.370.346.463.3
BaseModel=OLMo-7B2026.0771.966.745.261.3
OPSD-StandardModel=OLMo-7B2026.0769.765.641.759
OPSD-PMIModel=R1-Distill-7B2026.0755.341.126.140.8
OPSD-StandardModel=R1-Distill-7B2026.0752.238.124.438.2
BaseModel=R1-Distill-7B2026.075239.624.438.7