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

Physical Perception on PAI-Bench

68.5PAI-Bench Score

GPT-5

39.17246.78654.462.014Feb 5, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.02
68.5
2026.02
57.7
2026.02
57.6
2026.02
55.4
2026.02
50.6
2026.02
48.1
2026.02
42.7
2026.02
41.7
2026.02
40.3