Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Computer-use Task Execution on Celestia
Loading...
24.2
Success Rate
ACuRL
12.656
15.653
18.65
21.647
Feb 10, 2026
Success Rate
Updated 1mo ago
Evaluation Results
Method
Method
Links
Success Rate
ACuRL
Training Environment=C...
2026.02
24.2
ACuRL
Training Environment=I...
2026.02
23.2
ACuRL
Training Environment=C...
2026.02
23.2
ACuRL
Training Environment=T...
2026.02
22.2
ACuRL
Training Environment=K...
2026.02
22.2
ACuRL
Training Environment=C...
2026.02
22.2
ACuRL
Training Environment=I...
2026.02
20.2
ACuRL
Training Environment=T...
2026.02
20.2
ACuRL
Training Environment=I...
2026.02
19.2
ACuRL
Training Environment=K...
2026.02
19.2
UI-TARS-1.5-7B
Iteration=N/A
2026.02
17.2
ACuRL
Training Environment=W...
2026.02
17.2
ACuRL
Training Environment=W...
2026.02
17.2
ACuRL
Training Environment=W...
2026.02
17.2
ACuRL
Training Environment=C...
2026.02
16.2
ACuRL
Training Environment=T...
2026.02
16.2
ACuRL
Training Environment=K...
2026.02
14.2
ACuRL
Training Environment=C...
2026.02
13.2
ACuRL
Training Environment=C...
2026.02
13.1
Feedback
Search any
task
Search any
task