OpenAI's finance AI scores 69.9%. Build a 50-question eval harness for your own documents.
This story is from 2026-09-11. It is preserved in the archive; the latest stories are on the live feed.
ChatGPT for Financial Services arrived on 10 September with a benchmark score attached: a shade under seventy per cent correct across a large pile of treasury filings. Strong number, honestly reported by OpenAI. It also tells you almost nothing about your documents. That is not a complaint about th…
Read the full story at DEV Community — AI ↗
Timeline · 1 report
- 2026-09-11 08:53 · DEV Community — AI
OpenAI's finance AI scores 69.9%. Build a 50-question eval harness for your own documents.