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

Multiple-choice Question Answering on MMLU-ProX

82.6Average Accuracy

ORACLE

21.55237.40153.2569.099Apr 18, 2026Apr 19, 2026Apr 20, 2026Apr 21, 2026Apr 22, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.04
82.685.485.58584.283.385.582.880.670.8--
2026.04
77.980.881.380.579.278.780.779.57664.6--
2026.04
77.780.38180.37978.580.579.575.664.5--
2026.04
69.280.580.879.777.975.480.135.769.343.4--
2026.04
65.471.372.371.467.364.47263.962.743.6--
2026.04
58.56467.166.16155.766.655.954.236--
2026.04
58.364.36766.26156.566.651.356.135.8--
2026.04
53.957.859.958.754.552.959.65649.936.2--
2026.04
53.663.86665.457.853.465.540.251.618.8--
2026.04
25.3-----------
2026.04
25.2-----------
2026.04
24.6-----------
2026.04
24.5-----------
2026.04
23.9-----------