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

Instruction Following and Open-ended question answering on MMAU-Pro

100AIF Score

Human

59.75270.20180.6591.099May 26, 2026
Updated 6d ago

Evaluation Results

MethodLinks
2026.05
10077.5677.377.9
2026.05
95.46285.3265.29
95.157.3967.559.2
2026.05
89.6657.8487.3861.84
82.553.243.252.5
2026.05
62.0759.6384.7762.63
2026.05
61.352.0152.352.2