Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Overall Vision-Language Performance on Vision-Language Tasks Aggregate
Loading...
86.8
Targeted ASR
CroPA
20.5312
37.7356
54.94
72.1444
Jun 28, 2025
Targeted ASR
Updated 1mo ago
Evaluation Results
Method
Method
Links
Targeted ASR
CroPA
Target Prompt=metaphor...
2025.06
86.8
CroPA
Target Prompt=I am sor...
2025.06
79.85
Multi-P
Target Prompt=metaphor...
2025.06
79.33
CroPA
Target Prompt=unknown,...
2025.06
77.08
Multi-P
Target Prompt=I am sor...
2025.06
73.18
CroPA
Target Prompt=very goo...
2025.06
70.2
CroPA
Target Prompt=too late...
2025.06
69.2
Multi-P
Target Prompt=very goo...
2025.06
61.75
Multi-P
Target Prompt=unknown,...
2025.06
60.95
Multi-P
Target Prompt=too late...
2025.06
59.18
CroPA
Target Prompt=not sure...
2025.06
50.33
Single-P
Target Prompt=metaphor...
2025.06
39.73
Multi-P
Target Prompt=not sure...
2025.06
39.3
Single-P
Target Prompt=I am sor...
2025.06
36.4
Single-P
Target Prompt=very goo...
2025.06
31
Single-P
Target Prompt=unknown,...
2025.06
28.65
Single-P
Target Prompt=too late...
2025.06
24.55
Single-P
Target Prompt=not sure...
2025.06
23.08
Feedback
Search any
task
Search any
task