Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Visual Probing on VisualProbe Easy
Loading...
70.2
Accuracy
Mini-o3
17.056
30.853
44.65
58.447
Jun 11, 2026
Accuracy
Updated 1mo ago
Evaluation Results
Method
Method
Links
Accuracy
Mini-o3
Model Type=Tool-Augmented
2026.06
70.2
GPT-5
Model Type=Commercial
2026.06
62.4
Gemini-2.5-Pro
Model Type=Commercial
2026.06
62.1
PERIA-8B
Model Type=Proposed
2026.06
61.7
Qwen3-235B
Model Type=Open-Source
2026.06
58.8
InternVL3.5-14B
Model Type=Open-Source
2026.06
58.1
Qwen3-32B
Model Type=Open-Source
2026.06
57.4
InternVL3.5-8B
Model Type=Open-Source
2026.06
54.7
Qwen3-8B
Model Type=Backbone Ba...
2026.06
54.6
Qwen3-30B
Model Type=Open-Source
2026.06
51.7
w/o RL
Model Type=Ablation
2026.06
51
Gemini-2.5-Flash
Model Type=Commercial
2026.06
46.1
R1-OneVision-7B
Model Type=Tool-Augmented
2026.06
39.2
w/o Tool
Model Type=Ablation
2026.06
36.1
VTool-R1-7B
Model Type=Tool-Augmented
2026.06
30.5
w/o SFT
Model Type=Ablation
2026.06
19.1
Feedback
Search any
task
Search any
task