Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Vision-Language Understanding on Vision-Language Benchmarks Easy Partition
Loading...
61.1
RealWorldQA Accuracy
Qwen2-VL-2B
59.956
60.253
60.55
60.847
Mar 24, 2026
RealWorldQA Accuracy
SQA Accuracy
GQA Accuracy
MME Accuracy
MSTAR Accuracy
POPE Accuracy
TextVQA Accuracy
AI2D Accuracy
Average Accuracy (Easy Partition)
Updated 24d ago
Evaluation Results
Method
Method
Links
RealWorldQA Accuracy
SQA Accuracy
GQA Accuracy
MME Accuracy
MSTAR Accuracy
POPE Accuracy
TextVQA Accuracy
AI2D Accuracy
Average Accuracy (Easy Partition)
Qwen2-VL-2B
Backbone=Qwen2-VL-2B
2026.03
61.1
78.1
60.2
75.3
43.6
87.7
79.3
70.4
69.5
VISOR
Backbone=Qwen2-VL-2B
2026.03
60
82.1
60.8
75.1
49.2
88.9
76.1
75
70.9
Feedback
Search any
task
Search any
task