OpenAI Deep Research
Ranked 3 of 6 research agents by recommenders
People recommend it for thorough, flexible research that surfaces far more sources than a search engine. The most common caveat is that Pro subscribers get only five full runs per month, after which critics say the limited version is weak.
People recommend it for thorough, flexible research that surfaces far more sources than a search engine. The most common caveat is that Pro subscribers get only five full runs per month, after which critics say the limited version is weak.
28 people gave an opinion
- recommend it
- 13
- criticize it
- 15
- approval share
- 46%
Recommended in 8 of 13 months
- November 2025: recommended
- December 2025: recommended
- January 2026: recommended
- February 2026: recommended
- March 2026: not recommended
- April 2026: recommended
- May 2026: recommended
- June 2026: recommended
- July 2026: recommended
- August 2026: not recommended
- September 2026: not recommended
- October 2026: not recommended
- November 2026: not recommended (month in progress)
Why it doesn’t carry the badge
- 13 people recommend itNeeds 10 or more, met.
- 0.8 recommenders for every criticNeeds 2 to 1 or better, not met.
- Recommended in 8 of 13 monthsNeeds 4 or more, met.
The same three rules apply to every product, and the badge can’t be bought. How the badge works
What people say about it
The reasons people give, with the number of comments that give each one. Open a reason to read what they said.
Why people recommend it
Each mark is one comment
Strong overall quality and accuracy
“Very few mistakes and lots more flexibility and understanding than the travel agents I used before.”
Comment from 9 Jun 2026 in “Siri AI” “the OpenAI offering has become genuinely amazing”
Comment from 2 Dec 2025 in “OpenAI declares 'code red' as Google catches up in AI race” “the recommendations still seem mostly “correct””
Comment from 3 Nov 2025 in “Tongyi DeepResearch – open-source 30B MoE Model that rivals OpenAI DeepResearch” - Comment from 27 May 2026 in “Big Tech's Anti-Labor Playbook Has Come for Wikipedia”
Broad, fast source surveying
“As it can quickly survey hundreds of sources for overall relevance”
Comment from 9 Apr 2026 in “Research-Driven Agents: What Happens When Your Agent Reads Before It Codes” “It is absolutely a better-Google-than-Google class of resource.”
Comment from 24 Feb 2026 in “Ask HN: How to exhaustively search the scientific literature?” Better than other research tools
“It is absolutely a better-Google-than-Google class of resource.”
Comment from 24 Feb 2026 in “Ask HN: How to exhaustively search the scientific literature?” “OpenAI Deep Research does a much better job”
Comment from 27 May 2026 in “Big Tech's Anti-Labor Playbook Has Come for Wikipedia” Valuable research input for LLMs
“I almost exclusively use Deep Research as inputs to LLMs for deeper domain knowledge”
Comment from 10 Nov 2025 in “Tongyi DeepResearch – open-source 30B MoE Model that rivals OpenAI DeepResearch” “Deep Research is invaluable”
Comment from 9 Jan 2026 in “AI solves Erdos problem #728 (Terence Tao mathstodon post)”
What people warn about
Each mark is one comment
Quality has declined over time
“Deep Research (though I swear it was better when I could choose o3)”
Comment from 12 Nov 2025 in “GPT-5.1: A smarter, more conversational ChatGPT” “I used to like OpenAI Deep Research, but then switched”
Comment from 25 Feb 2026 in “Mercury 2: The fastest reasoning LLM, powered by diffusion” “(OpenAI's has really gone downhill for some reason.)”
Comment from 20 Feb 2026 in “Nvidia and OpenAI abandon unfinished $100B deal in favour of $30B investment” - Comment from 16 Aug 2026 in “ChatGPT lost 22 points of web share in a year”
Skips items or gives thin results
“Repeatedly it would take shortcuts and not actually do the full list.”
Comment from 3 Nov 2025 in “Tongyi DeepResearch – open-source 30B MoE Model that rivals OpenAI DeepResearch” “got a handful of results, but nothing comprehensive”
Comment from 24 Feb 2026 in “Ask HN: How to exhaustively search the scientific literature?”
Other research agents people recommend
The four most recommended other research agents, with the same counts for each, so you can compare like for like. The tick on each bar marks the 2 to 1 line the badge needs.
| Product | Recommend | Criticize | Approval | Months | Owned | Badge |
|---|---|---|---|---|---|---|
| Autoresearch by Karpathy | 37 | 15 | 71% | 6 | — | Approved |
| Gemini Deep Research | 27 | 19 | 59% | 9 | — | — |
| OpenAI Deep ResearchThis page | 13 | 15 | 46% | 8 | — | — |
| Kagi Research | 9 | 0 | 100% | 7 | — | — |
| LangAlpha | 8 | 2 | 80% | 1 | — | — |
What people said
26 of the 28 comments that mention it, newest first. Each links to the original comment.
“ChatGPT nerfed its Deep Research offering”
“That approach won't give you access to the "Pro Mode" nor "Deep Research" though”
“But it had fabricated the entire report. Nothing in it was true.”
“Subtly different prompts that by all means should still produce the same factual outcome”
“Very few mistakes and lots more flexibility and understanding than the travel agents I used before.”
“OpenAI Deep Research does a much better job”
“the second I have to pay even 2x the price I won't use that anymore”
“it works much better than even chatgpt, gemini or claude deep research outputs”
“but it still needs improvement”
“As it can quickly survey hundreds of sources for overall relevance”
“could not be iterative and future proof as new evidence comes to light”
“I used to like OpenAI Deep Research, but then switched”
“got a handful of results, but nothing comprehensive”
“It is absolutely a better-Google-than-Google class of resource.”
“is largely garbage, especially for goods where the infosphere is dominated by the manufacturers”
“(OpenAI's has really gone downhill for some reason.)”
“Deep Research is invaluable”
“Deep Research works better than OpenAI's deep research given their search expertise.”
“it’s weird and forced because it asks one series of questions”
“Pro subscribers get only five per month. After that, it's a limited version, and it's not good”
“the OpenAI offering has become genuinely amazing”
“Deep Research (though I swear it was better when I could choose o3)”
“I almost exclusively use Deep Research as inputs to LLMs for deeper domain knowledge”
“making it for many cases the least useful research agent”
“Repeatedly it would take shortcuts and not actually do the full list.”
“the recommendations still seem mostly “correct””
Counts come from 1,795,640 Hacker News comments, November 2025 to November 2026. How we count. Report a mistake.