List your company

Mathematical Reasoning on DeepMath500

69Pass@1 RateBaseline LLM
41.64848.74955.8562.951Mar 4, 2026

Evaluation results

MethodLinks
Baseline LLMSystem Category=Standalone2026.036914,882100
COREA *System Category=Collaborative2026.0367.513,88259.9
Brier-SLM-VerbSystem Category=Collaborative2026.0366.315,25472.5
RLVR-SLM-ProbeSystem Category=Collaborative2026.0363.39,56241.7
Router+RLVR-SLMSystem Category=Collaborative2026.0361.47,65935.6
SLM-VerbSystem Category=Collaborative2026.0360.311,59443.6
RLVR-SLMSystem Category=Standalone2026.0357.62,5110
RLVR-SLM-VerbSystem Category=Collaborative2026.0357.62,6721
RLVR-SLM-AvgProbSystem Category=Collaborative2026.0357.62,5110
L1-SLM*System Category=Standalone2026.0356.63,7660
Brier-SLMSystem Category=Standalone2026.0355.73,4900
SLMSystem Category=Standalone2026.0342.74,4230