Computer-use Task Execution on Writer
15.6Success RateACuRL
Evaluation Results
| Method | Links | |
|---|---|---|
| ACuRLTraining Environment=Writer, Iteration=Iter 32026.02 | 15.6 | |
| ACuRLTraining Environment=Celestia, Iteration=Iter 12026.02 | 15.3 | |
| ACuRLTraining Environment=Celestia, Iteration=Iter 22026.02 | 15.3 | |
| ACuRLTraining Environment=Celestia, Iteration=Iter 32026.02 | 15.3 | |
| ACuRLTraining Environment=Impress, Iteration=Iter 22026.02 | 15 | |
| ACuRLTraining Environment=Impress, Iteration=Iter 32026.02 | 14.4 | |
| ACuRLTraining Environment=Writer, Iteration=Iter 22026.02 | 14.2 | |
| ACuRLTraining Environment=Calc, Iteration=Iter 12026.02 | 13.3 | |
| ACuRLTraining Environment=KAlgebra, Iteration=Iter 12026.02 | 13.3 | |
| ACuRLTraining Environment=Impress, Iteration=Iter 12026.02 | 13 | |
| ACuRLTraining Environment=Writer, Iteration=Iter 12026.02 | 13 | |
| ACuRLTraining Environment=Calc, Iteration=Iter 22026.02 | 12.8 | |
| ACuRLTraining Environment=Thunderbird, Iteration=Iter 22026.02 | 12.5 | |
| ACuRLTraining Environment=Thunderbird, Iteration=Iter 12026.02 | 12.2 | |
| ACuRLTraining Environment=Calc, Iteration=Iter 32026.02 | 11.7 | |
| ACuRLTraining Environment=KAlgebra, Iteration=Iter 32026.02 | 11.7 | |
| ACuRLTraining Environment=KAlgebra, Iteration=Iter 22026.02 | 11.6 | |
| UI-TARS-1.5-7BIteration=N/A2026.02 | 10.8 | |
| ACuRLTraining Environment=Thunderbird, Iteration=Iter 32026.02 | 9.5 |