Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Affordance Reasoning on Affordance Dataset Setting A S S 1.0 (test)
Loading...
96.2
Accuracy
A4D
43.16
56.93
70.7
84.47
Jun 4, 2026
Accuracy
Updated 1mo ago
Evaluation Results
Method
Method
Links
Accuracy
A4D
Weight Freezing Strate...
2026.06
96.2
A4D
Weight Freezing Strate...
2026.06
94.2
A4D
Weight Freezing Strate...
2026.06
87.5
GPT-5.4
Scale=medium, Latency...
2026.06
78.9
GPT-5.4
Scale=low, Latency (ms...
2026.06
73.1
GPT-5-mini
Latency (ms)=3,900
2026.06
70.2
GPT-5-nano
Prompting Strategy=CoT...
2026.06
63.5
SigLIP
Evaluation Protocol=ze...
2026.06
62.5
ViLT-B32
Evaluation Protocol=VQ...
2026.06
58.7
GPT-5-nano
Prompting Strategy=sta...
2026.06
53.8
CLIP
Evaluation Protocol=ze...
2026.06
48.1
BLIP
Evaluation Protocol=ze...
2026.06
45.2
Feedback
Search any
task
Search any
task