Deep Research Agent

About this leaderboard

Evaluates long-horizon research agents on multi-hop reasoning, source aggregation, citation faithfulness, synthesis clarity, and domain breadth (STEM, humanities, policy).

We stress-test models with curated simulations that blend structured benchmarks and open-ended prompts. Each table captures a distinct slice of the use case, and models are compared consistently across shared metrics to surface leaders, trade-offs, and surprising strengths.