Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Zero-shot Language Understanding and Reasoning Suite (PIQA, ARC, HellaSwag, WinoGrande, BoolQ, LAMBADA, C4)

79.67PIQA Accuracy

L2QER

72.036474.01827677.9818Mar 26, 2026
Updated 22d ago

Evaluation Results

MethodLinks
2026.03
79.6749.3380.6766.6774.3380.33769.6372.43
2026.03
79.675181.336674.3382799.5973.33
2026.03
7950.3381.6766.337282779.7872.62
2026.03
78.6751.6780.6767.6774.6780.6779973.29
2026.03
78.3359.3380.3366.6775.679266.3313.0874.1
2026.03
78.3359.337865.6773926213.7972.62
2026.03
78.3356.3379.6766.6775.3391.6764.6713.873.24
2026.03
7851.3381.6768.677684.3374.339.8773.48
2026.03
77.6756.678068.8775.6791.3366.6713.2673.84
2026.03
77.675779.3367.6774.3391.3365.3313.4873.24
2026.03
77.6739.67726470.3374.3370.3310.9866.9
2026.03
77.33538363.6768.678767.6714.5271.48
2026.03
77.3339.6771.676469.6771.6770.3311.0766.33
2026.03
7751.3380.336974.3382.6775.339.6872.86
2026.03
76.9857.6779.336774926513.2973.14
2026.03
76.6752.3380.3364.677186.3363.6714.670.71
2026.03
76.6738.6772.3361.6768.6772.3364.6711.0465.48
2026.03
76.3351.337962.3369.6785.6764.6714.7869.86
2026.03
76.3350.6780.6763.3370.678565.3314.7770.29
2026.03
75.6752.3380.33637185.3363.671570.19
2026.03
75.6751.3379.3362.6767.6785.3364.6714.8269.52
2026.03
75.3339.3373.3360.6768.6774.6765.6711.4565.38
2026.03
75.334071.676468.3373.3368.3311.0466.19
2026.03
72.3339.3372.3363.6770.33777110.367.14