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

Instruction Following Evaluation on HelpSteer2 (val)

71.8Quality

SEE

56.92860.78964.6568.511Jun 3, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.06
71.870.9--
2026.06
70.473.167.170
2026.06
69.167--
2026.06
68.265.1--
2026.06
66.267.55761.7
2026.06
64.463.25050
2026.06
59.967--
2026.06
58.162.1--
2026.06
57.558.5--