List your company

Common Sense Reasoning on HellaSwag (Delta Score)

0.34HellaSwag DeltaFLOATDOOR
0.03840.11670.1950.2733Jun 17, 2026

Evaluation results

MethodLinks
FLOATDOORScenario=M22026.060.34
FLOATDOORScenario=S12026.060.32
FLOATDOORScenario=S22026.060.32
FLOATDOORScenario=M12026.060.26
FLOATDOORScenario=S32026.060.05