Exchange

Find

Answer from contract paragraphs

Pick · 10 Nov

Highest (right answers per dollar) among models at least 90% right; no pick if none qualify.

Claude Haiku 5.5

2,400 right answers per $1

$0.41 per 1,000 right

Buy at Anthropic (opens Anthropic, another site)

Model comparison

How the models compare

50 items, same for every model.
ModelRight (%)Cost per 1,000 right
Claude Haiku 5.5Pick100$0.41
GLM-5.3 Flash98$0.53
Gemini 3.1 Flash Lite100$0.58
GPT-6 Luna86$0.23

The test

Goes in
A question with contract paragraphs
Comes out
An answer and the paragraphs it cites
Right means
Right answer, citing only the documents that apply
Checked by
A script

Models testedPreview Desk

Desk · Not open yet.

If another company’s model has higher than Desk that day, we’ll link you to the highest- model before you send a job. You will still be able to use Desk.