CLClawBench
ClawBench is an open-source benchmark for evaluating browser AI agents on everyday tasks across live production websites, with isolated runs and five-layer execution traces.
Open-source projects by this author in the catalog, across all categories and statuses.
1 Projects
CLClawBench is an open-source benchmark for evaluating browser AI agents on everyday tasks across live production websites, with isolated runs and five-layer execution traces.