Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Robotic Manipulation on LIBERO Specialized Suites & Diverse Suite
Loading...
85
Metric 90 Success Rate
Argos
76.992
79.071
81.15
83.229
Dec 3, 2025
Metric 90 Success Rate
Object Success Rate
Spatial Success Rate
Goal Success Rate
Long-Horizon Success Rate
Average Success Rate
Updated 4d ago
Evaluation Results
Method
Method
Links
Metric 90 Success Rate
Object Success Rate
Spatial Success Rate
Goal Success Rate
Long-Horizon Success Rate
Average Success Rate
Argos
training_stage=MMRL
2025.12
85
93.2
91.2
87.8
63.8
84.2
Qwen2.5-VL-7B
training_stage=SFT
2025.12
83.3
88
91
84
66.1
82.4
Video-R1
training_stage=SFT
2025.12
82.7
88.2
91
85.2
64
82.2
Qwen2.5-VL-7B
training_stage=Base
2025.12
82.3
84
93.6
80.6
60.2
80.1
Video-R1
training_stage=Post-train
2025.12
80.1
89.2
93
89.6
65.6
83.5
Qwen2.5-VL-7B-Instruct
training_stage=Instruct
2025.12
77.3
81.6
93.4
84.4
62.4
79.8
Feedback
Search any
task
Search any
task