Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Multimodal Comprehension on Hallusion
Loading...
50.9
Score
Qwen2-VL
32.908
37.579
42.25
46.921
Feb 22, 2026
Score
Updated 4d ago
Evaluation Results
Method
Method
Links
Score
Qwen2-VL
Model Size=7B, Trainin...
2026.02
50.9
CREM_G
Model Size=7B, Trainin...
2026.02
49.2
CREM
Model Size=7B, Trainin...
2026.02
48.8
CREM_R
Model Size=7B, Trainin...
2026.02
44.5
Qwen2-VL
Model Size=2B, Trainin...
2026.02
41.9
CREM
Model Size=2B, Trainin...
2026.02
41.2
CREM_G
Model Size=2B, Trainin...
2026.02
41
CREM_R
Model Size=2B, Trainin...
2026.02
33.6
Feedback
Search any
task
Search any
task