The docs q&a leaderboard · for knowledge workers

Best for docs q&a

Decision area
Grounded answers over your own knowledge base.
Editor picks
5 editor picks
Eligible models
11 eligible models
See raw /best
EDITOR'S CHOICEResearched 34d ago

Claude Sonnet 4.6

Anthropic · 1M context
Excellent

Models for answering questions from your own documents.

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

The numbers
$/1M out
$15.00
$3.00 input
Context
1M
max window
Pros
  • +Strong groundedness
  • +Refuses cleanly off-context
  • +1M context
Cons
  • −$15 / 1M out

Also worth picking

The runners-up

ranked by editorial pick orderEditorial tiersExcellentStrongSolid
Anthropic · 1M
$10.00 / 1M out
1M window at $2 / $10 per 1M tokens, enough to put medium document sets in a single prompt.
Anthropic · 1M
$0.50 / 1M out
$0.10 / $0.50 per 1M tokens for prompts up to 100K tokens, for high-volume chat over your documents. Longer prompts are billed at $0.50 / $2.50.
OpenAI · 1.05M
$10.00 / 1M out
1.05M window at $2 / $10 per 1M tokens, with code interpreter for questions over spreadsheets and files.
DeepSeek · 1M
$0.73 / 1M out
Open weights, 1M context, cheap — strong self-hosted RAG backend.

Eligibility

11 models are eligible for this board

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