Computer-use Task Execution on KAlgebra
28Success RateACuRL
Evaluation Results
| Method | Links | |
|---|---|---|
| ACuRLTraining Environment=KAlgebra, Iteration=Iter 32026.02 | 28 | |
| ACuRLTraining Environment=KAlgebra, Iteration=Iter 22026.02 | 20.5 | |
| ACuRLTraining Environment=Calc, Iteration=Iter 22026.02 | 19.4 | |
| ACuRLTraining Environment=KAlgebra, Iteration=Iter 12026.02 | 18.3 | |
| ACuRLTraining Environment=Writer, Iteration=Iter 32026.02 | 17.2 | |
| ACuRLTraining Environment=Calc, Iteration=Iter 32026.02 | 16.1 | |
| ACuRLTraining Environment=Celestia, Iteration=Iter 22026.02 | 15 | |
| ACuRLTraining Environment=Celestia, Iteration=Iter 32026.02 | 15 | |
| ACuRLTraining Environment=Impress, Iteration=Iter 12026.02 | 14 | |
| ACuRLTraining Environment=Impress, Iteration=Iter 22026.02 | 14 | |
| ACuRLTraining Environment=Writer, Iteration=Iter 12026.02 | 14 | |
| ACuRLTraining Environment=Thunderbird, Iteration=Iter 32026.02 | 14 | |
| ACuRLTraining Environment=Impress, Iteration=Iter 32026.02 | 12.9 | |
| ACuRLTraining Environment=Calc, Iteration=Iter 12026.02 | 12.9 | |
| ACuRLTraining Environment=Celestia, Iteration=Iter 12026.02 | 11.8 | |
| UI-TARS-1.5-7BIteration=N/A2026.02 | 10.8 | |
| ACuRLTraining Environment=Writer, Iteration=Iter 22026.02 | 10.8 | |
| ACuRLTraining Environment=Thunderbird, Iteration=Iter 12026.02 | 10.8 | |
| ACuRLTraining Environment=Thunderbird, Iteration=Iter 22026.02 | 8.6 |