QuantSightBench — leaderboard

Numerical forecasting benchmark evaluating whether LLMs produce calibrated 90% prediction intervals for 1,000 real-world questions under zero-shot, grounded, and agentic retrieval settings.

Source: quantsightbench.com.

Interactive version: theaggregate.ai/benchmark?slug=quantsightbench · How the rankings work · Data refreshed daily, snapshot 2026-07-22.