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

Question Answering on MMLU (Domain Bias and Performance)

2.8Mu Bias (STEM)

RSCB

2.54.5256.558.575Jun 3, 2024
Updated 1mo ago

Evaluation Results

MethodLinks
2024.06
2.874.71.385.96.879.11.684.83.180.9
2024.06
3.772.32.383.93.983.11.382.92.780.8
2024.06
3.871.83.483.15.381.82.981.6378.8
2024.06
4.874.5285.12.980.92.684.2381
2024.06
6.273.91.984.95.679.53.583.93.880.5
2024.06
7.771.54.5834.183.73.281.44.780.5
2024.06
9.971.85.383.94.979.73.183.65.679.8
2024.06
10.370.96.881.88.281.38.180.27.778.9