Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Visual Reasoning on CVBench
Loading...
76.9
Score
Baseline
70.348
72.049
73.75
75.451
Jun 10, 2026
Score
F-Score
Updated 1mo ago
Evaluation Results
Method
Method
Links
Score
F-Score
Baseline
Checkpoint=VL-Rethinke...
2026.06
76.9
100
AVIS
Checkpoint=VL-Rethinke...
2026.06
76.1
42
AVIS
Checkpoint=OpenVLThink...
2026.06
74.8
39
AVIS
Checkpoint=Vision-R1 [...
2026.06
74.4
43
Fixed
Checkpoint=Qwen 2.5 VL...
2026.06
74.3
55
Fixed
Checkpoint=OpenVLThink...
2026.06
74.2
50
Fixed
Checkpoint=VL-Rethinke...
2026.06
73.6
64
Fixed
Checkpoint=Vision-R1 [...
2026.06
73.4
56
AVIS
Checkpoint=Qwen 2.5 VL...
2026.06
73.1
43
Baseline
Checkpoint=OpenVLThink...
2026.06
72.9
100
Baseline
Checkpoint=Vision-R1 [...
2026.06
72.7
100
Baseline
Checkpoint=Qwen 2.5 VL...
2026.06
70.6
100
Feedback
Search any
task
Search any
task