Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
End-to-end Question Answering on InfoSeek 25-sample perturbed subset
Loading...
52
Rotation
Oracle
31.2
36.6
42
47.4
Feb 13, 2026
Rotation
Flip
Brightness
Blur
Gaussian Noise
Crop
Expand
Overlay
Watermark
RealWorld
Average Accuracy
Updated 1mo ago
Evaluation Results
Method
Method
Links
Rotation
Flip
Brightness
Blur
Gaussian Noise
Crop
Expand
Overlay
Watermark
RealWorld
Average Accuracy
Oracle
Pre-processing strateg...
2026.02
52
56
44
44
40
40
64
48
56
44
49.3
V-QPP(SFT)
Pre-processing strateg...
2026.02
48
48
44
48
48
40
36
40
60
44
45.4
Imperfect
Pre-processing strateg...
2026.02
44
40
48
52
44
40
16
44
12
12
37.6
V-QPP
Pre-processing strateg...
2026.02
32
32
44
36
40
36
24
36
8
0
30.8
Feedback
Search any
task
Search any
task