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

General Language Understanding on 10 Benchmarks Average (test)

67.4Accuracy (Average)

Base

25.48836.36947.2558.131Mar 23, 2026Mar 30, 2026Apr 6, 2026Apr 14, 2026Apr 21, 2026Apr 28, 2026May 6, 2026
Updated 27d ago

Evaluation Results

MethodLinks
2026.05
67.4-
2026.03
63.74.12
2026.03
62.53.88
2026.03
62.14.04
2026.03
61.93.88
2026.05
61.6-
2026.03
59.71.71
2026.05
59.2-
2026.05
57.1-
2026.05
53.3-
2026.05
49.6-
2026.05
45.2-
2026.05
39.5-
2026.05
37.4-
2026.03
27.1-