Continuing the discussion from Decsion Api now available in public beta
We are benchmarking OpenAI’s Decision API vs Jev vs our own Financial World Model.
Can anyone share standard financial reasoning, decision-making, and forecasting evaluation tests or benchmarks for comparison?
Looking for reproducible benchmarks, especially for credit risk, fraud detection, financial document reasoning, and GNPA prediction.
Would love to collaborate with anyone working on Financial AI evaluation or with design partners