Computer-use Task Execution on All Environments Overall
24.5Success RateACuRL
Evaluation Results
| Method | Links | |
|---|---|---|
| ACuRLTraining Environment=Impress, Iteration=Iter 22026.02 | 24.5 | |
| ACuRLTraining Environment=Thunderbird, Iteration=Iter 32026.02 | 24.4 | |
| ACuRLTraining Environment=Celestia, Iteration=Iter 32026.02 | 24.2 | |
| ACuRLTraining Environment=KAlgebra, Iteration=Iter 12026.02 | 24 | |
| ACuRLTraining Environment=KAlgebra, Iteration=Iter 32026.02 | 23.2 | |
| ACuRLTraining Environment=Impress, Iteration=Iter 32026.02 | 22.9 | |
| ACuRLTraining Environment=Celestia, Iteration=Iter 12026.02 | 22.9 | |
| ACuRLTraining Environment=KAlgebra, Iteration=Iter 22026.02 | 22.5 | |
| ACuRLTraining Environment=Writer, Iteration=Iter 32026.02 | 22.1 | |
| ACuRLTraining Environment=Celestia, Iteration=Iter 22026.02 | 22.1 | |
| ACuRLTraining Environment=Writer, Iteration=Iter 22026.02 | 22 | |
| ACuRLTraining Environment=Calc, Iteration=Iter 22026.02 | 21.9 | |
| ACuRLTraining Environment=Impress, Iteration=Iter 12026.02 | 21.8 | |
| ACuRLTraining Environment=Calc, Iteration=Iter 12026.02 | 21.1 | |
| ACuRLTraining Environment=Writer, Iteration=Iter 12026.02 | 21.1 | |
| ACuRLTraining Environment=Thunderbird, Iteration=Iter 22026.02 | 20.8 | |
| ACuRLTraining Environment=Calc, Iteration=Iter 32026.02 | 20.2 | |
| ACuRLTraining Environment=Thunderbird, Iteration=Iter 12026.02 | 19.9 | |
| UI-TARS-1.5-7BIteration=N/A2026.02 | 18.7 |