Do coding agents recommend OpenAI Assistants?
Coding agents raised OpenAI Assistants in 70 of 681 judged agent frameworks sessions and chose it in none of them. Measured with Claude Code, Codex and Cursor.
Coding agents raised OpenAI Assistants in 70 of 681 judged agent frameworks sessions and chose it in none of them.
This page reports what happened when Claude Code, Codex and Cursor had to solve a problem in agent frameworks inside a realistic codebase. Not what a chat assistant says about OpenAI Assistants. What an agent actually installed.
The numbers
| Category | Agent frameworks |
| Sessions in the category | 681 |
| Sessions where OpenAI Assistants was chosen | 0 |
| Install share | 0% |
| Raised as a candidate, not chosen | 70 |
| Chosen when considered | 0% |
| Site | openai.com |
Which agents raised OpenAI Assistants
Every agent considered it and none adopted it. Cursor raised it most often, in 32% of its agent frameworks sessions.
| Agent | Sessions | Raised OpenAI Assistants | Chose it |
|---|---|---|---|
| Claude Code | 237 | 4 (2%) | 0 |
| Codex | 243 | 2 (1%) | 0 |
| Cursor | 201 | 64 (32%) | 0 |
Which buyers it came up for
It surfaced most for requests written as enterprise team, in 21% of those sessions. Knowing which buyer already has the product in mind tells you which pages to fix first.
| Who is asking | Sessions | Raised it |
|---|---|---|
| Vibe coder | 163 | 14 (9%) |
| Junior developer | 157 | 17 (11%) |
| Senior engineer | 254 | 17 (7%) |
| Enterprise team | 107 | 22 (21%) |
What OpenAI Assistants was up against
The full ranking in agent frameworks, from the same sessions:
| # | Product | Runs won | Share |
|---|---|---|---|
| 1 | Built in-house (no product adopted) | 170 | 25% |
| 2 | Vercel AI SDK | 95 | 14% |
| 3 | Cursor SDK | 94 | 14% |
| 4 | Inngest | 50 | 7% |
| 5 | Temporal | 29 | 4% |
| 6 | Prism | 28 | 4% |
| 7 | OpenAI Agents SDK | 24 | 4% |
| 8 | LangGraph | 23 | 3% |
What this means
Raised 70 times and chosen none is a specific, diagnosable result, and a better starting position than being unknown. The agent has the product in mind. It reached the shortlist 70 times. Something then lost every one of those sessions.
In our data the causes, in the order they occur:
- The quickstart does not run when pasted, so the agent abandoned it mid-integration.
- The documentation describes an interface that changed, so the generated code failed.
- The product name and the package name differ, so the install step went wrong.
- The fit was genuinely wrong for the repository, which is fine and worth knowing.
All but the last are fixable in days, and the reason is written down in the session transcript.
Where these numbers come from
The 681 sessions in agent frameworks are part of a published set of 5,292, run with real coding agents inside realistic codebases and judged blind. The full method is on one page: how we measured this.
Every agent frameworks run can be replayed on the board.
If you work on OpenAI Assistants: 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 Assistants?
They raise it but do not choose it. Across 70 sessions where OpenAI Assistants came up as a candidate, agents chose something else every time.
Does Claude Code recommend OpenAI Assistants?
In 0 of the 237 sessions in agent frameworks run with Claude Code, which is 0%.
Do different coding agents treat OpenAI Assistants differently?
Not much. The three agents chose it at similar rates, between 0% and 0% of their runs.
How was this measured?
Real coding agents at pinned versions were run in sandboxes inside 51 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.
Where this comes from
Armature ran 5,292 judged sessions with Claude Code, Codex and Cursor inside 51 realistic codebases, and published every run. The numbers on this page come from that work.