Agentic browsing

DeepSearchQA

Questions that cannot be answered from one page: the AI has to search the web, follow the trail across several sources, and put the pieces together into an answer. Higher is better.

Rankings

Higher is better

DeepSearchQA — frequently asked questions

What is DeepSearchQA?
Questions that cannot be answered from one page: the AI has to search the web, follow the trail across several sources, and put the pieces together into an answer. Higher is better.
Which AI model scores highest on DeepSearchQA?
Muse Spark 1.3 by Meta holds the best DeepSearchQA result among tracked models, at 89.4% (released Sep 2 2026). Higher scores are better on this benchmark.
What are the top 1 models on DeepSearchQA?
1. Muse Spark 1.3 (Meta) — 89.4%.
How many models have a published DeepSearchQA score?
1 tracked model has a published DeepSearchQA score. Scores are the figures reported by each lab at that model's release, so this page is a record of results over time rather than a re-run leaderboard.