List your company

Clarifying Questions on OpenBookQA (test)

28AccuracyRefit
9.2814.141923.86Jun 8, 2025

Evaluation results

MethodLinks
RefitMode=Thinking Mode2025.0628264.555.555.324.374.954.94
SwiftMode=Thinking Mode2025.0624464.675.75.394.415.135.23
StepDPOMode=Thinking Mode2025.0620264.275.315.014.074.674.73
BaseMode=Thinking Mode2025.0610474.895.935.634.65.375.35
DPOMode=Thinking Mode2025.0610304.275.295.054.044.754.87
STaR-GATE-DMode=Thinking Mode2025.061044.115.134.853.814.424.59