Gemini Deep Research
Gemini's research mode: it plans a search, reads widely and writes a cited report.
By Google · launched 2024-12-11 · last checked 2026-11-01
Why 4: given a question, it browses and writes a cited report on its own for you to check afterwards; it acts only when asked, so not a 5.
What it does. Deep Research launched for Gemini Advanced subscribers on 11 December 2024. On 11 December 2025 Google released a stronger version built on Gemini 3 Pro, available to developers through the Interactions API and as an upgrade in the Gemini app, and claimed 59.2% on OpenAI's BrowseComp benchmark.
Where it falls short. The benchmark figure is Google's own. An April 2026 study found that 3–13% of citation URLs from commercial models and deep research agents likely never existed, with deep research agents fabricating at higher rates.
What it can do
Incidents
- None logged.
Closest fiction
Her — Samantha reading at superhuman speed.
Related research agents
- ChatGPT deep research OpenAI · autonomy 4/5
- Perplexity Deep Research Perplexity · autonomy 4/5
History
- 2026-11-01 Added to the index.
Sources
- Try Deep Research and our new experimental model in Gemini, your AI assistant Google, 2024-12-11
- Build with Gemini Deep Research Google, 2025-12-11
- Detecting and Correcting Reference Hallucinations in Commercial LLMs and Deep Research Agents arXiv (Rao, Wong and Callison-Burch), 2026-04-03
← All agents in the index · Autonomy is rated on what the product does today, on a 1–5 scale. Every fact links to a source.