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

Question Answering on MMLU-PRO (test) Subject Scores and Pass@1

56.37Pass@1 Accuracy

RLVR

34.956440.515746.07551.6343Oct 10, 2025Nov 18, 2025Dec 28, 2025Feb 6, 2026Mar 18, 2026Apr 27, 2026Jun 6, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2025.10
56.3772.1162.9651.8657.3442.39
2025.10
55.1270.8361.5952.2256.2841.3
2025.10
54.8270.2561.4551.8756.1340.27
2025.10
54.0570.2960.7153.2756.140.56
2025.10
53.0670.0561.2351.1156.3239.87
2025.10
52.8270.7161.7249.5657.5637.46
2025.10
48.7259.5559.748.2352.4434.47
2026.06
44.68-----
2026.06
42.21-----
2026.06
41.92-----
2026.06
41.71-----
2026.06
40.71-----
2026.06
35.78-----