Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Turn off lightbulb on CALVIN
Loading...
100
Success Rate
WAM
-4
23
50
77
Mar 30, 2026
Apr 8, 2026
Apr 18, 2026
Apr 28, 2026
May 8, 2026
May 18, 2026
May 28, 2026
Success Rate
Environment Steps (DiWA)
Updated 5d ago
Evaluation Results
Method
Method
Links
Success Rate
Environment Steps (DiWA)
WAM
Fine-tuning Protocol=O...
2026.03
100
-
BC+RL
Method=BC+RL, Future C...
2026.05
100
-
BC+RL
Method=BC+RL, Future C...
2026.05
94
-
BC+RL
Method=BC+RL, Future C...
2026.05
91.1
-
DiWA
Fine-tuning Protocol=O...
2026.03
82.33
-
DiWA
Fine-tuning Protocol=O...
2026.03
77.01
-
WAM
Fine-tuning Protocol=O...
2026.03
75.9
-
Diffusion Policy
Fine-tuning Protocol=B...
2026.03
68.8
-
Diffusion Policy
Fine-tuning Protocol=B...
2026.03
17.2
-
BC+RL
Method=BC+RL, Future C...
2026.05
0
-
DPPO
Vision Encoder Type=Vi...
2026.03
-
327,066
DPPO
Vision Encoder Type=Vi...
2026.03
-
1,260,000
DPPO
Vision Encoder Type=Vi...
2026.03
-
277,333
DPPO
Vision Encoder Type=Vi...
2026.03
-
184,800
Feedback
Search any
task
Search any
task