Search and deep research / Benchmark leaderboard

GAIA

Multi-step questions requiring tools, browsing, files and sometimes multimodal inputs.

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-answer accuracy by difficulty level.

Execution requirements

General agent with the required tool and media access.

Scope and limitations

Gated access; the Harbor package has 165 tasks, a public validation subset rather than the entire hidden evaluation.

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

Exa: Research endpoint or composite system

Glean: Capability-aligned; adapter/access to qualify

OpenAI: Capability-aligned; adapter/access to qualify

Parallel: Research endpoint or composite system

Perplexity: Capability-aligned; adapter/access to qualify

Tavily: Research endpoint or composite system

Writer: Capability-aligned; adapter/access to qualify

You.com: Research endpoint or composite system