From the source
Hugging Face and collaborators propose FutureBench, a benchmark that evaluates AI agents on their ability to predict future events using real-world prediction markets and news.
Back to The Future: Evaluating AI Agents on Predicting Future Events
Research paper
From the source
We therefore propose evaluating agents on their ability to predict future events (Ye et al., 2024; Karger et al., 2025). FutureBench draws from real-world prediction markets and emerging news to create interesting prediction tasks grounded in actual future outcomes.
huggingface.co
