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

Affordance Reasoning on Affordance Dataset Setting B: S/U 1.0 (test)

85.4Accuracy

GPT-5-mini

15.51233.65651.869.944Jun 4, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.06
85.4
2026.06
85.4
2026.06
83.9
2026.06
82.3
2026.06
82.3
2026.06
70.8
2026.06
60.8
2026.06
56.2
2026.06
50.8
2026.06
36.9
2026.06
30.8
2026.06
18.2