List your company

ResearchFormerly WizWand

Cross-application Task Execution

Benchmarks

DatasetSOTA methodMetricTrendResultsLast updated

LibreOffice Calc 45 tasks

Experience Bank

46.7Pass Rate

3

Apr 14, 2026

VS Code 30 tasks

Experience Bank

63.3Pass Rate

3

Apr 14, 2026

Chrome 45 tasks

Distillation + Experience Bank

77.8Pass Rate

3

Apr 14, 2026