Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Zero-shot Evaluation on ARC-e, BoolQ, HellaSwag, LAMBADA, PIQA, RACE, SocialIQA, SciQ, and SWAG

77.9ARC-e Accuracy

JREG

53.9860.1966.472.61Jan 26, 2026
Updated 4d ago

Evaluation Results

MethodLinks
2026.01
77.961.650.357.275.237.842.59351.560.8
2026.01
75.659.449.755.976.536.343.993.451.360.2
2026.01
70.659.342.645.671.834.941.491.247.356.1
2026.01
69.461.443.147.271.835.342.188.647.656.2
2026.01
68.561.442.946.672.432.94189.547.355.8
2026.01
57.26032.131.765.229.938.881.140.248.5
2026.01
57.26032.431.665.128.94081.739.948.5
2026.01
5757.132.530.76529.338.682.24048
2026.01
56.160.532.229.865.629.639.280.939.948.2
2026.01
5659.232.231.76529.138.182.24048
2026.01
55.758.332.432.565.929.638.681.340.248.3
2026.01
54.957.532.1326429.138.480.239.747.5