Research6h ago
New Benchmark Finds AI Lags in Finance
The Deep FinResearch Bench evaluates AI agents on qualitative rigor, forecasting accuracy, and claim credibility. Researchers compared frontier agents against human professionals, finding that AI-generated reports consistently underperform across all three dimensions. This gap proves that general-purpose models struggle with professional investment research. Practitioners must prioritize domain-specific fine-tuning to achieve institutional quality.