Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Visual Question Answering on IrSD-VQA
Loading...
82
Accuracy
SpatialPIN
52.88
60.44
68
75.56
Mar 18, 2024
Accuracy
Numerical Output Rate
Accuracy (Range 50-200)
Accuracy (Range 75-133)
Accuracy (Range 90-111)
Updated 1mo ago
Evaluation Results
Method
Method
Links
Accuracy
Numerical Output Rate
Accuracy (Range 50-200)
Accuracy (Range 75-133)
Accuracy (Range 90-111)
SpatialPIN
Backbone=GPT-4o
2024.03
82
-
-
-
-
GPT-4o
Backbone=GPT-4o
2024.03
64
-
-
-
-
SpatialVLM
Backbone=PaLM 2-E
2024.03
54
-
-
-
-
GPT-4o
2024.03
-
30
10
4
2
GPT-4o + SpatialPIN
Backbone=GPT-4o
2024.03
-
100
68
54
38
SpatialVLM
Backbone=PaLM 2-E
2024.03
-
78
26
12
4
Feedback
Search any
task
Search any
task