The docs q&a leaderboard · for knowledge workers

Best for docs q&a

4 editor picks · 5 eligible models · Grounded answers over your own knowledge base.

EDITOR'S CHOICEResearched 1d ago

Claude Sonnet 4.6

Anthropic · 1M context

Excellent

The safest grounded-QA pick in production.

Highest groundedness and graceful refusal — says "not in the docs" instead of guessing.

The numbers

$/1M out

$15.00

$3.00 input

Context

max window

Pros

Cons

Also worth picking

ranked by editorial pick order

Editorial tiersExcellentStrongSolid

#ModelTier$/1M outEditor's note

Google DeepMind · 1M

$5.00

A 1M window lets you skip retrieval entirely on medium corpora.

Anthropic · 200K

$4.00

Almost as grounded as Sonnet at a fraction of the price — the default for chat-on-docs.

DeepSeek · 1M

$0.87

Open weights, 1M context, cheap — strong self-hosted RAG backend.

Eligibility

Eligibility means tagged with useCases: [docs-qa]. Pins must come from this pool.