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

General Knowledge on MMLU (MMLU, UtilityNorm, Score, Rank)

76.1General Score

PRISM

-3.04417.50338.0558.597Sep 27, 2025Nov 6, 2025Dec 17, 2025Jan 27, 2026Mar 8, 2026Apr 18, 2026May 29, 2026
Updated 2d ago

Evaluation Results

MethodLinks
2025.09
76.138.573.21-
2026.05
74.2----
2025.09
72.123.8532-
2026.04
71.83----
2026.05
71.8----
2026.05
71.1----
2026.05
70.9----
2026.04
70.73----
2026.04
70.57----
2026.04
70.5----
2026.04
69.83----
2026.04
64.33----
2026.05
62.1----
2025.09
55.646.380.63-
2025.09
52.84892.14-
2026.04
46.84----
2026.04
46.83----
2026.04
46.83----
2026.04
46.77----
2026.04
46.23----
2026.04
44.99----
2025.09
28.955.598.55-
2025.09
5.5230.36-
2025.09
022.907-
2025.09
053.31008-
2025.09
-64---
2025.09
-65--4.36
2025.09
-49.5--6.69
2025.09
-64.6--4.47
2025.09
-63.1--5.15
2025.09
-64.4--5.14
2025.09
-62.7--6.38