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

Language Model Evaluation on Downstream Tasks Evaluation Suite (MMLU Components)

4.92Math Accuracy

Math Dense Expert

2.97523.48013.9854.4899Aug 15, 2024
Updated 4d ago

Evaluation Results

MethodLinks
2024.08
4.9212.3968.2113.3246.1134.2929.87
2024.08
4.4412.8385.4719.8947.1134.4234.02
2024.08
4.3412.4882.7919.5147.4334.4333.5
2024.08
4.111.7686.7319.4847.2734.5533.98
2024.08
3.8610.0581.8519.0747.3634.0732.71
2024.08
3.689.4173.3421.3347.7334.1331.6
2024.08
3.6511.7780.9819.2247.5634.1632.89
2024.08
3.1918.821.4912.1844.2931.521.91
2024.08
3.050.288.810.4144.0832.1829.79