Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Discriminative Task on AMBER Discrimination 1.0 (test)
Loading...
76.7
Accuracy
Octopus
66.612
69.231
71.85
74.469
Mar 1, 2025
Accuracy
F1 Score
Updated 1mo ago
Evaluation Results
Method
Method
Links
Accuracy
F1 Score
Octopus
Backbone=LLaVA-1.5-7B,...
2025.03
76.7
82.7
Octopus
Backbone=InstructBLIP,...
2025.03
74
79.7
AVISC
Backbone=InstructBLIP,...
2025.03
72.6
78.6
AVISC
Backbone=LLaVA-1.5-7B,...
2025.03
70.7
75.45
VCD
Backbone=InstructBLIP,...
2025.03
69.65
75.9
M3ID
Backbone=InstructBLIP,...
2025.03
69.05
75.25
InstructBLIP
Backbone=InstructBLIP,...
2025.03
68.2
74.6
VCD
Backbone=LLaVA-1.5-7B,...
2025.03
67.3
71.1
M3ID
Backbone=LLaVA-1.5-7B,...
2025.03
67.25
70.9
LLaVA-1.5-7B
Backbone=LLaVA-1.5-7B,...
2025.03
67
71.1
Feedback
Search any
task
Search any
task