Hebbia sees improvements in financial research with GPT-6 Astra
Summary
Hebbia, a financial research platform, tested OpenAI's GPT-6 Astra to improve two key tasks: finding relevant sources for financial questions and building presentation decks that follow a banker's brief. In tests using hypothetical financial research cases, GPT-6 Astra scored 13.6 percentage points above the best alternative on citing required source types, with 99.5% of cited excerpts relevant to the question. It also met 97.9% of presentation requirements, 14.4 percentage points ahead of the best alternative, ranking first on both adherence to brief and presentation quality. Hebbia emphasizes traceability, as users can open citations to see underlying documents. The model's ability to produce precise, guideline-adherent outputs could save professionals hours by reducing deck reformatting and source-checking, bringing first drafts closer to final output. Hebbia also envisions a future role for agents that monitor information and surface signals for finance professionals.
(Source:OpenAI)