Retrieval, embeddings and long context / Benchmark leaderboard

BRIGHT

Retrieval requiring reasoning beyond lexical or simple semantic matching.

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

nDCG@10 and domain breakdowns.

Execution requirements

Retrieval/reranker or agentic retrieval system.

Scope and limitations

Good complement to BEIR; label query expansion, reasoning model and additional compute.

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

Cohere: Direct component API + selected system adapters

Exa: Research endpoint or composite system

Glean: Capability-aligned; adapter/access to qualify

Jina AI: Direct component API + selected system adapters

Pinecone: Composite system

Vectara: Capability-aligned; adapter/access to qualify

Voyage AI: Direct component API + selected system adapters

Weaviate: Composite system

Qdrant: A configured retrieval pipeline must use the original corpus, exclusions and evaluator; disclose embeddings and any query reasoning.