A new benchmark, Investor's Last Exam, evaluates whether AI agents can perform equity investment research using only decision-time evidence, with their forecasts and investment judgments scored against subsequent market outcomes. The benchmark is designed to test the full research process rather than financial knowledge or isolated forecasting, and requires a strictly frozen information cutoff so agents cannot see future data. Existing benchmarks cover financial knowledge, research workflows, or forecasting, but not the complete investment process under these constraints.
Financial agents must form forecasts and investment judgments from decision-time evidence, with predictions evaluated against subsequent outcomes. Existing benchmarks assess financial knowledge, research workflows, or forecasting, but evaluating the full research process requires a strictly frozen i
EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.