List your company

Dialog on Life Services In-Domain

86.73AccuracyBaseline
26.9342.45557.9873.505Feb 5, 2026

Evaluation results

MethodLinks
BaselineTraining Steps=10002026.0286.73
DFPOTraining Steps=10002026.0285.67
Reinforce++Training Steps=10002026.0285.17
PPOTraining Steps=10002026.0259.2
Dr.GRPOTraining Steps=10002026.0244.67
GRPOTraining Steps=10002026.0229.23