ForecastBench

A dynamic, continuously updated benchmark developed and maintained by the Forecasting Research Institute to evaluate large language models’ forecasting accuracy on automatically generated time-series questions and prediction-market questions, comparing model performance to human superforecasters and the general public.

Endorsements support Forecasting Research Institute.

No endorsements yet.

Discussion

Start Date

-

End Date

-

Expected Duration

-

Funding Raised to Date

-