Computer-use Task Execution on Calc
9Success RateACuRL
Evaluation Results
| Method | Links | |
|---|---|---|
| ACuRLTraining Environment=Calc, Iteration=Iter 32026.02 | 9 | |
| ACuRLTraining Environment=Impress, Iteration=Iter 22026.02 | 8.1 | |
| ACuRLTraining Environment=Calc, Iteration=Iter 22026.02 | 7.8 | |
| ACuRLTraining Environment=Calc, Iteration=Iter 12026.02 | 7.5 | |
| ACuRLTraining Environment=Thunderbird, Iteration=Iter 32026.02 | 7.5 | |
| ACuRLTraining Environment=Celestia, Iteration=Iter 32026.02 | 7.5 | |
| ACuRLTraining Environment=Writer, Iteration=Iter 32026.02 | 7.4 | |
| ACuRLTraining Environment=KAlgebra, Iteration=Iter 22026.02 | 7.1 | |
| ACuRLTraining Environment=Writer, Iteration=Iter 12026.02 | 6.9 | |
| ACuRLTraining Environment=Thunderbird, Iteration=Iter 12026.02 | 6.6 | |
| UI-TARS-1.5-7BIteration=N/A2026.02 | 6.5 | |
| ACuRLTraining Environment=KAlgebra, Iteration=Iter 12026.02 | 6.5 | |
| ACuRLTraining Environment=Impress, Iteration=Iter 12026.02 | 5.9 | |
| ACuRLTraining Environment=Impress, Iteration=Iter 32026.02 | 5.9 | |
| ACuRLTraining Environment=Writer, Iteration=Iter 22026.02 | 5.6 | |
| ACuRLTraining Environment=Thunderbird, Iteration=Iter 22026.02 | 5.6 | |
| ACuRLTraining Environment=Celestia, Iteration=Iter 12026.02 | 5.6 | |
| ACuRLTraining Environment=KAlgebra, Iteration=Iter 32026.02 | 5.3 | |
| ACuRLTraining Environment=Celestia, Iteration=Iter 22026.02 | 5 |