Terminal X says its Eval Agent matches senior investor judgment 88.6% with GPT-6.1
Overview
Terminal X says its Eval Agent matches senior investor judgment 88.6% of the time when built on GPT-6.1 Sol.
The agent grades outputs against a 54-criterion rubric and catches 25% more deviations from a fund's mandate, according to a first-party OpenAI News report.
The figures come from Terminal X's own account of its agent. The report does not describe how the agreement rate was measured or who the senior investors were.
Written by AI from the articles below · updated Oct 20, 10:31 PM ET
Check the sources:
Article timeline
The articles in this story. Times are ET.
- OpenAI NewsOfficialTerminal X matches senior investor judgment 88.6% with GPT-6.1
AITerminal X says its Eval Agent matches senior investor judgment 88.6% of the time, using GPT-6.1 Sol. The agent grades outputs against a 54-criterion rubric and catches 25% more deviations from a fund's mandate.
Heat Trend
Not enough continuous observations to show a trend yet.