Terminal X Reports 88.6% Reviewer Agreement for GPT-6.1 Sol

In a customer profile, OpenAI says Terminal X's Eval Agent running GPT-6.1 Sol agreed with a senior human reviewer on 88.6% of 500 scored investment judgments. The next best model reached 86.4%, a difference of 220 basis points.

The Eval Agent grades investment analysis using a rubric with 54 criteria, including source selection, numerical comparisons, narrative consistency and fit with a fund's mandate. Terminal X says GPT-6.1 Sol caught about 25% more recommendations that departed from a fund's mandate and ran the same workflows at about 30% lower cost per query than the next best model.

Terminal X uses GPT-6.1 Sol for tasks that require judgment and large context windows, while GPT-6 Luna handles higher volume work. The company says it has created 1,700 firm Memories and completed more than 1 million custom workflows. One private equity customer reported $2.4 million in annualized savings from automated due diligence and investment memo work.