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

General Language Understanding on 10-benchmark suite average

73.81Average Accuracy

FP

48.142854.806461.4768.1336Jun 4, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.06
73.81
2026.06
73.53
2026.06
72.75
2026.06
72.4
2026.06
71.94
2026.06
71.38
2026.06
71.34
2026.06
71.05
2026.06
67.4
2026.06
66.83
2026.06
62.12
2026.06
61.09
2026.06
59.37
2026.06
58.78
2026.06
49.13