List your company

General Reasoning on English Reasoning Suite Aggregate

66.26AccuracyGenKnowSub
63.743264.396665.0565.7034May 16, 2025

Evaluation results

MethodLinks
GenKnowSubBase Model=Phi-2, Setting=En, Evaluation Protocol=zero-shot2025.0566.26
GenKnowSubBase Model=Phi-2, Setting=Avg, Evaluation Protocol=zero-shot2025.0566.19
ArrowBase Model=Phi-2, Evaluation Protocol=zero-shot2025.0565.15
Phi-2Base Model=Phi-2, Evaluation Protocol=zero-shot2025.0563.84