Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Multi-step Visual Reasoning on Multi-step Reasoning Suite (train)
Loading...
0.3
Average Tool Calls
VTool-R1
0.092
1.496
2.9
4.304
Apr 21, 2026
Average Tool Calls
Updated 1mo ago
Evaluation Results
Method
Method
Links
Average Tool Calls
VTool-R1
Zoom-in=–, Rotate=–, F...
2026.04
0.3
ReVPT
Zoom-in=✓, Rotate=–, F...
2026.04
0.6
OpenThinkIMG
Zoom-in=✓, Rotate=–, F...
2026.04
0.7
Pixel Reasoner
Zoom-in=✓, Rotate=–, F...
2026.04
0.8
DeepEyes
Zoom-in=✓, Rotate=–, F...
2026.04
1
ToolsRL
Zoom-in=✓, Rotate=✓, F...
2026.04
3.4
Mini-o3
Zoom-in=✓, Rotate=–, F...
2026.04
5.5
Feedback
Search any
task
Search any
task