Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Visual Probing on VisualProbe Medium
Loading...
52.9
Accuracy
Mini-o3
10.364
21.407
32.45
43.493
Jun 11, 2026
Accuracy
Updated 1mo ago
Evaluation Results
Method
Method
Links
Accuracy
Mini-o3
Model Type=Tool-Augmented
2026.06
52.9
PERIA-8B
Model Type=Proposed
2026.06
41.2
Gemini-2.5-Pro
Model Type=Commercial
2026.06
38.7
w/o RL
Model Type=Ablation
2026.06
37.3
Gemini-2.5-Flash
Model Type=Commercial
2026.06
36
Qwen3-32B
Model Type=Open-Source
2026.06
32
Qwen3-235B
Model Type=Open-Source
2026.06
32
Qwen3-8B
Model Type=Backbone Ba...
2026.06
31.3
Qwen3-30B
Model Type=Open-Source
2026.06
30.2
VTool-R1-7B
Model Type=Tool-Augmented
2026.06
26.4
InternVL3.5-8B
Model Type=Open-Source
2026.06
25.7
R1-OneVision-7B
Model Type=Tool-Augmented
2026.06
21.7
GPT-5
Model Type=Commercial
2026.06
21.6
w/o Tool
Model Type=Ablation
2026.06
21.2
w/o SFT
Model Type=Ablation
2026.06
18.6
InternVL3.5-14B
Model Type=Open-Source
2026.06
12
Feedback
Search any
task
Search any
task