NEWS · COMPANIES · #2303
Terminal X Eval Agent matches senior investor judgment 88.6% using GPT-6.1 Sol
Terminal X says its Eval Agent grades outputs against a 54-criterion rubric and, when powered by GPT-6.1 Sol, matched senior investor judgment 88.6% of the time and identified 25% more deviations from a fund’s mandate.
KEY POINTS
- Terminal X says its Eval Agent grades outputs against a 54-criterion rubric and, when powered by GPT-6.1 Sol, matched senior investor judgment 88.6% of the time and identified 25% more deviations from a fund’s mandate.
- If accurate, this suggests large language models can approximate experienced investor assessments and improve automated detection of mandate deviations, affecting asset-management review workflows.
- Terminal X matches senior investor judgment 88.6% with GPT-6.1
WHY IT MATTERS
If accurate, this suggests large language models can approximate experienced investor assessments and improve automated detection of mandate deviations, affecting asset-management review workflows.