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

Instruction Following on IFEval (IFScore)

84.63IFScore

Gemini2.5-Flash

33.867647.046360.22573.4037Sep 9, 2025Oct 20, 2025Nov 30, 2025Jan 10, 2026Feb 20, 2026Apr 2, 2026May 14, 2026
Updated 19d ago

Evaluation Results

MethodLinks
2025.09
84.63
2025.09
80.39
2025.09
73.72
2025.09
70.47
2025.09
66.83
2025.09
66.69
2025.09
61.29
2026.05
56
2026.05
55.1
2026.05
54.9
2026.05
54.9
2026.05
54.8
2026.05
54.7
2026.05
54.2
2026.05
54.1
2026.05
53.9
2025.09
50.83
2025.09
44.51
2026.05
43.6
2025.09
40.02
2025.09
35.82