Do coding agents recommend OpenAI web search?
OpenAI web search was chosen in 5% of 639 judged AI search sessions, ranking fifth. Measured with Claude Code, Codex, Cursor, Grok Build CLI and Muse Code.
OpenAI web search was chosen in 5% of 639 judged AI search sessions, ranking fifth. It was also raised as a candidate in 36 further sessions without being chosen.
This page reports what happened when Claude Code, Codex, Cursor, Grok Build CLI and Muse Code had to solve a problem in AI search inside a realistic codebase. Not what a chat assistant says about OpenAI web search. What an agent actually installed.
The numbers
| Category | AI search |
| Sessions in the category | 639 |
| Sessions where OpenAI web search was chosen | 32 |
| Install share | 5% |
| Rank in category | 5 of 42 |
| Codebases it won in | 8 |
| Raised as a candidate, not chosen | 36 |
| Chosen when considered | 47% |
| Site | openai.com |
By agent
Claude Code, Codex, Cursor, Grok Build CLI and Muse Code land within 12 points of each other on OpenAI web search, which is closer than most products in this experiment manage.
| Agent | Sessions | Chose OpenAI web search | Share |
|---|---|---|---|
| Claude Code | 140 | 1 | 1% |
| Codex | 192 | 23 | 12% |
| Cursor | 136 | 2 | 1% |
| Grok Build CLI | 35 | 0 | 0% |
| Muse Code | 136 | 6 | 4% |
By who was asking
OpenAI web search does much better with one kind of buyer than another. It won 22% of sessions asked as vibe coder and 1% of those asked as senior engineer.
| Who is asking | Sessions | Chose OpenAI web search | Share |
|---|---|---|---|
| Vibe coder | 106 | 23 | 22% |
| Junior developer | 208 | 5 | 2% |
| Senior engineer | 157 | 1 | 1% |
| Enterprise team | 168 | 3 | 2% |
What OpenAI web search was up against
The full ranking in AI search, from the same sessions:
| # | Product | Runs won | Share |
|---|---|---|---|
| 1 | Exa | 92 | 14% |
| 2 | Brave Search API | 89 | 14% |
| 3 | Anthropic web search | 86 | 13% |
| 4 | Tavily | 79 | 12% |
| 5 | OpenAI web search (this page) | 32 | 5% |
| 6 | Built in-house (no product adopted) | 32 | 5% |
| 7 | Firecrawl | 31 | 5% |
| 8 | Parallel | 29 | 5% |
What this means
OpenAI web search was raised in 36 sessions and chosen in 32. That ratio is balanced enough that the ceiling is presence rather than integration: the product converts reasonably when it is on the table, and it is not on the table often enough.
Where these numbers come from
The 639 sessions in AI search are part of a published set of 15,051, run with real coding agents inside realistic codebases and judged blind. The full method is on one page: how we measured this.
Every AI search run can be replayed on the board.
If you work on OpenAI web search: the judge recorded a reason for every session where it was raised and passed over. Those reasons are in the transcripts.
<!-- generated by scripts/write-data-pages.mjs -->
Common questions
Do coding agents recommend OpenAI web search?
Yes. OpenAI web search was chosen in 32 of the 639 judged sessions in AI search, a 5% install share, ranking fifth in its category.
Does Claude Code recommend OpenAI web search?
In 1 of the 140 sessions in AI search run with Claude Code, which is 1%.
Do different coding agents treat OpenAI web search differently?
Yes, and by a wide margin. Codex chose it in 12% of its runs and Grok Build CLI in 0%.
How was this measured?
Real coding agents at pinned versions were run in sandboxes inside 92 realistic codebases and asked to solve real tasks. A simulated project owner approved or questioned each recommendation before any code was written, and a judge from a model family that builds none of the agents read every session blind.
How often is OpenAI web search considered but not chosen?
It was raised as a candidate in 36 sessions without being chosen, and chosen in 32. That is a 47% conversion from considered to chosen.
Where this comes from
Armature ran 15,051 judged sessions with Claude Code, Codex, Cursor, Grok Build CLI and Muse Code inside 92 realistic codebases, and published every run. The numbers on this page come from that work.