Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Pick on Real Robot Manipulation real-world
Loading...
86
Success Rate
Claude Sonnet 4.5
-3.44
19.78
43
66.22
Dec 3, 2025
Success Rate
TTFM (s)
Updated 4d ago
Evaluation Results
Method
Method
Links
Success Rate
TTFM (s)
Claude Sonnet 4.5
zero-shot=true, Toolsh...
2025.12
86
30
SpaceTools
interactive RL=true
2025.12
86
10
GPT-5
zero-shot=true, Toolsh...
2025.12
71
36
π0.5
type=Vision-Language A...
2025.12
0
1
Qwen2.5-VL-3B
zero-shot=true, Toolsh...
2025.12
0
-
Feedback
Search any
task
Search any
task