Computer-use Task Execution on Thunderbird
57.8Success RateACuRL
Evaluation Results
| Method | Links | |
|---|---|---|
| ACuRLTraining Environment=Thunderbird, Iteration=Iter 32026.02 | 57.8 | |
| ACuRLTraining Environment=Impress, Iteration=Iter 22026.02 | 51.1 | |
| ACuRLTraining Environment=Writer, Iteration=Iter 22026.02 | 51.1 | |
| ACuRLTraining Environment=KAlgebra, Iteration=Iter 12026.02 | 51.1 | |
| ACuRLTraining Environment=KAlgebra, Iteration=Iter 32026.02 | 48.9 | |
| ACuRLTraining Environment=Celestia, Iteration=Iter 12026.02 | 48.9 | |
| ACuRLTraining Environment=Celestia, Iteration=Iter 32026.02 | 48.9 | |
| ACuRLTraining Environment=Calc, Iteration=Iter 22026.02 | 46.7 | |
| ACuRLTraining Environment=KAlgebra, Iteration=Iter 22026.02 | 46.7 | |
| ACuRLTraining Environment=Impress, Iteration=Iter 12026.02 | 44.5 | |
| ACuRLTraining Environment=Calc, Iteration=Iter 12026.02 | 44.5 | |
| ACuRLTraining Environment=Writer, Iteration=Iter 12026.02 | 44.5 | |
| ACuRLTraining Environment=Writer, Iteration=Iter 32026.02 | 44.4 | |
| ACuRLTraining Environment=Thunderbird, Iteration=Iter 12026.02 | 42.2 | |
| ACuRLTraining Environment=Thunderbird, Iteration=Iter 22026.02 | 42.2 | |
| ACuRLTraining Environment=Celestia, Iteration=Iter 22026.02 | 42.2 | |
| ACuRLTraining Environment=Impress, Iteration=Iter 32026.02 | 40 | |
| ACuRLTraining Environment=Calc, Iteration=Iter 32026.02 | 37.8 | |
| UI-TARS-1.5-7BIteration=N/A2026.02 | 35.5 |