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

Language Understanding on MMLU mimicked

72.5Algebra Score

GPT-4

14.98829.91944.8559.781Feb 19, 2024
Updated 1mo ago

Evaluation Results

MethodLinks
2024.02
72.591.676.385.291.6
2024.02
52.670.254.462.575.6
2024.02
41.577.962.573.577.1
2024.02
37.780.65573.581.9
2024.02
37.682.658.971.979.7
2024.02
36.685.257.471.582
2024.02
35.581.459.470.281.4
2024.02
2977.23650.172
2024.02
27.977.145.759.374.4
2024.02
26.773.343.661.972.9
2024.02
17.26832.349.860.6