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

Instruction Following on IFBench (Score)

75.4IFBench Score

GPT-5.2

16.43231.74147.0562.359Oct 2, 2025Oct 31, 2025Nov 29, 2025Dec 28, 2025Jan 26, 2026Feb 24, 2026Mar 26, 2026
Updated 22d ago

Evaluation Results

MethodLinks
2026.03
75.4
2026.03
71.2
70.4
2026.03
69.7
2026.03
58.7
2026.03
38.33
2026.03
37.67
2026.03
36.33
2026.03
35.67
2026.03
35.65
2026.03
34.33
2026.03
33.6
2026.03
33.33
2026.03
31.67
2026.03
30.44
2026.03
27
2026.03
23.67
2025.10
20.7
2025.10
18.7