Terminal X uses GPT-6.1 Sol to evaluate investment agents
Terminal X uses OpenAI’s GPT-6.1 Sol and GPT-6 Luna in investment agents and an Eval Agent that checks outputs against a fund’s mandate. In Terminal X’s evaluation of 500 scored judgments, its Eval Agent on GPT-6.1 Sol agreed with a senior human reviewer 88.6% of the time, compared with 86.4% for the next-best model. It also caught about 25% more mandate deviations and ran the same workflows at roughly 30% lower cost per query at similar speed. A private equity firm reported $2.4 million in annualized savings from automated due-diligence and investment-memo workflows. The benchmark, cost comparison and savings figure came from Terminal X and its customer, not an independent evaluation.
The deployment shows how AI models are being used in an auditable investment-agent workflow, with model performance measured against senior reviewers and mandate-specific errors. It also illustrates how Terminal X uses task-specific evaluation results to choose models.
An investment firm’s edge is built deal by deal, but the judgment behind each decision usually lives in the heads of a few senior investors. When they leave, the firm takes on what Terminal X(opens in a new window) calls memory debt: the firm may keep the documents, but it loses the reasoning.
Terminal X’s Capital Memory operating system is designed to pay that debt down. The company’s forward-deployed engineers, former finance and investment professionals at JPMorgan and Blackstone, sit with each customer’s investment teams, design the firm’s agentic architecture, and encode how the firm invests into agents the firm owns, deployed on-premise or in its own cloud.
OpenAI models, including GPT‑6.1 Sol and GPT‑6 Luna, handle the reasoning inside those agents. And Terminal X’s Eval Agent grades the agents’ output against the firm’s standards. GPT‑6.1 Sol helped the Eval Agent catch about 25% more recommendations that strayed from a fund’s mandate and ran the same workflows at approximately 30% lower cost per query than the next-best model.
“GPT-6.1 Sol’s long-context reasoning and token efficiency allow us to build deeper evaluation pipelines. This helps our Eval Agents make investment judgment measurable and auditable.”
#Terminal X#OpenAI#GPT-6.1 Sol#GPT-6 Luna#Terminal X Capital Memory#Terminal X Eval Agent