Desktop and mobile agents / Benchmark leaderboard

OSWorld-Verified

Desktop tasks involving applications, files and cross-application workflows.

No published company result yet.

This benchmark is in the research directory. Its task package, adapter and grading protocol need qualification before a hosted run can be offered.

Arrange an evaluation for your company →

What this benchmark measures

Metrics

Final environment-state task success.

Execution requirements

Desktop VM, screenshot/input adapter and pinned OS image.

Scope and limitations

Harbor has 361 tasks and excludes eight Google Drive/login tasks; disclose this versus the original 369-task suite.

Evaluation availability

Catalog entry. Request a managed evaluation to qualify your agent interface and the benchmark’s native grading requirements.

Sources and company fit

Companies whose products may fit

Research recommendations based on product capabilities. These companies have not necessarily run this benchmark or integrated with Blobfish.

Compatibility notes for each company

Anthropic: Capability-aligned; adapter/access to qualify

Automation Anywhere: Product-specific adapter / qualified access

Google DeepMind: Capability-aligned; adapter/access to qualify

OpenAI: Capability-aligned; adapter/access to qualify

UiPath: Product-specific adapter / qualified access