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

Instruction Following on Ko-IFEval

93.2Overall Score

gpt-oss-120b

78.95282.65186.3590.049Jan 11, 2026Jan 22, 2026Feb 2, 2026Feb 13, 2026Feb 24, 2026Mar 7, 2026Mar 19, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.01
93.2
2026.03
93.2
2026.03
91
2026.03
88.19
2026.01
87.5
2026.03
87.45
2026.01
86.7
85.6
2026.03
85.13
2026.03
84.2
2026.03
81.03
2026.03
79.74
2026.01
79.5