Discover everything your finance AI needs from the web
Trusted by
The most accurate & efficient web search for finance
What this measures
This benchmark evaluates Opus 5.5’s accuracy and total cost (web search fees + token consumption) to answer complex questions about companies, litigation, financials, products, and industry news.
Methodology summary
We created a ground truth dataset for 250 questions that require company research by running Fable 5.1 with unlimited resources and manual verification. We then ran Opus 5.5 on high effort six times, each with a different web search provider, and compared the results against ground truth.
Finance web search use cases with Nimble
See our how-to blog for building financial analysis agents with Nimble
Gather any evidence to inform predictions
Research any thesis across the web and build a cited dataset of the evidence behind it.
Dive deep into any financial market
Map a market's size, players, and trends, down to the data buried in filings and filtered listings.
Source target companies and tear sheets
Find every company that matches your criteria, with a cited tear sheet for each.
Run deep due diligence on any company
Research financials, leadership, litigation, and reputation, with a confidence score on every finding.
Discover and retrieve alternative data at scale
Collect pricing, hiring, and product data across thousands of sites as structured datasets.
How Nimble discovers deep, trustworthy finance data
Get the precise data you asked for
Self-learning research agents optimize search & retrieval for specific tasks.
Access web data others can’t
Nimble doesn’t just retrieve search results, it browses sites to go deeper.
Retrieve data you can trust
Web search governance and confidence scoring to flag weak evidence.
How finance teams integrate Nimble
Embed research into your agent workflows
Via MCP, API or connectors
Ad hoc research through your personal AI
Like Codex, Claude Code, or Cursor
Build large-scale web datasets
Stream structured data into your datastore
