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

Zero-shot Performance on LMEval Harness Subset (HellaSwag, BoolQ, WinoGrande, PiQA, ARC)

75.46Mean Accuracy

GIFT-SW

40.079249.264658.4567.6354Aug 27, 2024Nov 22, 2024Feb 18, 2025May 17, 2025Aug 13, 2025Nov 9, 2025Feb 5, 2026
Updated 4d ago

Evaluation Results

MethodLinks
2024.08
75.46------
2024.08
75.29------
2024.08
74.84------
2024.08
74.5------
2024.08
74.37------
2024.08
74.34------
2026.02
74.3173.3280.979.2381.3177.7453.33
2024.08
74.27------
2024.08
73.27------
2026.02
73.2673.2480.2377.8880.1876.7651.26
2026.02
73.2373.6980.3478.1679.9976.4850.7
2026.02
73.2372.380.5279.3880.5877.5349.06
2026.02
73.0873.0980.2777.8379.9476.6250.72
2026.02
73.0573.1680.1278.1479.5876.6750.61
2026.02
72.9873.5180.1977.9780.287649.95
2026.02
72.872.3880.1178.6579.8676.9548.82
2026.02
72.7972.5879.8778.7579.9876.7948.75
2026.02
72.7171.8779.8378.880.0976.8848.82
2026.02
72.6772.0679.9978.7579.7976.6948.75
2026.02
72.6272.0679.9178.7879.4276.8348.72
2024.08
72.53------
2024.08
72.43------
2024.08
71.65------
2024.08
71.3------
2026.02
71.1171.1979.0775.9578.8574.9446.63
2024.08
71.08------
2026.02
71.0670.6979.4476.0378.3375.1846.72
2024.08
71------
2026.02
7170.8379.3676.3679.0574.1146.42
2026.02
70.9770.2679.1176.2478.9474.846.47
2026.02
70.9370.5479.2776.3279.0873.9146.45
2026.02
70.4769.0679.1175.9877.7474.6246.33
2024.08
70.24------
2024.08
69.82------
2026.02
69.6569.278.5875.1476.4173.4745.07
2026.02
69.5869.1478.475.1177.2573.1344.47
2026.02
69.5469.6978.4475.2176.7773.0444.11
2026.02
69.4968.8378.5675.0776.273.4944.81
2026.02
69.4369.7278.5275.1675.3273.344.57
2026.02
69.3370.6477.5673.2877.5571.6245.36
2024.08
67.61------
2026.02
67.670.4876.4373.0676.3667.5441.76
2026.02
67.3468.0277.471.6975.0770.1841.37
2026.02
66.8269.1475.5273.0773.7667.142.32
2026.02
66.8267.4877.6871.5572.9470.0241.26
2026.02
66.566.8477.0271.7374.1268.4940.79
2026.02
66.3466.7177.277273.168.1140.84
2026.02
66.1465.9776.7171.8873.1167.9341.21
2026.02
65.7769.6674.773.8974.7561.8939.76
2026.02
65.269.8274.9770.8171.2763.4740.84
2024.08
63.99------
2024.08
62.91------
2024.08
62.19------
2024.08
61.09------
2024.08
58.89------
2024.08
58.2------
2024.08
53.8------
2024.08
48.96------
2024.08
47.14------
2024.08
41.44------