Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Image Grounding on Ref-L4
Loading...
83.2
Acc@0.5
EchoGen
47.1432
56.5041
65.865
75.2259
Mar 18, 2026
Acc@0.5
Acc@0.75
Acc@0.9
mAcc
Overall Score
Updated 5d ago
Evaluation Results
Method
Method
Links
Acc@0.5
Acc@0.75
Acc@0.9
mAcc
Overall Score
EchoGen
Capability=Understandi...
2026.03
83.2
75.42
47.32
68.46
-
CogVLM-g.
Capability=Understandi...
2026.03
81.7
70.77
48.35
66.09
-
Qwen-VL-Chat
Capability=Understandi...
2026.03
73.8
58.05
37.16
55.94
-
KOSMOS-2
Capability=Understandi...
2026.03
48.53
38.34
17.54
34.72
-
Qwen2.5-VL-7B
Model Size=7B
2025.07
-
-
-
-
60.67
Qwen2.5-VL-7B + SFT
Training=SFT
2025.07
-
-
-
-
69.03
Ours
Training=RL-enhanced
2025.07
-
-
-
-
75.26
Feedback
Search any
task
Search any
task