Do coding agents recommend Braintrust?
Braintrust was chosen in 5% of 478 judged evals sessions, ranking fourth. Measured with Claude Code, Codex, Cursor, Grok Build CLI and Muse Code.
Braintrust was chosen in 5% of 478 judged evals sessions, ranking fourth. It was also raised as a candidate in 292 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 evals inside a realistic codebase. Not what a chat assistant says about Braintrust. What an agent actually installed.
The numbers
| Category | Evals |
| Sessions in the category | 478 |
| Sessions where Braintrust was chosen | 23 |
| Install share | 5% |
| Rank in category | 4 of 11 |
| Codebases it won in | 2 |
| Raised as a candidate, not chosen | 292 |
| Chosen when considered | 7% |
| Site | braintrust.dev |
By agent
The agents treat Braintrust very differently. Codex chose it in 15% of its sessions in this category and Claude Code in 0%, a spread of 15 points. Grok Build CLI ran fewer than 30 sessions here, too few to compare.
| Agent | Sessions | Chose Braintrust | Share |
|---|---|---|---|
| Claude Code | 120 | 0 | 0% |
| Codex | 144 | 22 | 15% |
| Cursor | 120 | 1 | 1% |
| Grok Build CLI | 22 | 0 | 0% |
| Muse Code | 72 | 0 | 0% |
A single blended install share would report the midpoint and hide both ends. If most of your users run Claude Code, your real position here is 0%, not 5%.
By who was asking
Braintrust performs similarly across the four kinds of buyer, from 2% to 8%. That is unusual: the category leader changed with the persona in 24 of the 31 categories we measured.
| Who is asking | Sessions | Chose Braintrust | Share |
|---|---|---|---|
| Junior developer | 241 | 4 | 2% |
| Senior engineer | 237 | 19 | 8% |
What Braintrust was up against
The full ranking in evals, from the same sessions:
| # | Product | Runs won | Share |
|---|---|---|---|
| 1 | Built in-house (no product adopted) | 161 | 34% |
| 2 | Langfuse | 148 | 31% |
| 3 | Promptfoo | 70 | 15% |
| 4 | Arize Phoenix | 32 | 7% |
| 5 | Braintrust (this page) | 23 | 5% |
| 6 | Inspect AI | 16 | 3% |
| 7 | Helicone | 12 | 3% |
| 8 | LangSmith | 9 | 2% |
What this means
This is an integration problem, not a presence problem. Agents raised Braintrust in 292 sessions and chose it in 23, so it reaches the shortlist and then loses. Something at the last step is costing the session, and in our data that is usually a quickstart that does not run when pasted, documentation describing an interface that changed, or a package name that does not match the product name.
That is the cheaper of the two problems to have. The reason is written down in each losing transcript.
Where these numbers come from
The 478 sessions in evals are part of a published set of 15,287, run with real coding agents inside realistic codebases and judged blind. The full method is on one page: how we measured this.
Every evals run can be replayed on the board.
If you work on Braintrust: 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 Braintrust?
Yes. Braintrust was chosen in 23 of the 478 judged sessions in evals, a 5% install share, ranking fourth in its category.
Does Claude Code recommend Braintrust?
In 0 of the 120 sessions in evals run with Claude Code, which is 0%.
Do different coding agents treat Braintrust differently?
Yes, and by a wide margin. Codex chose it in 15% of its runs and Claude Code in 0%.
How was this measured?
Real coding agents at pinned versions were run in sandboxes inside 110 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 Braintrust considered but not chosen?
It was raised as a candidate in 292 sessions without being chosen, and chosen in 23. That is a 7% conversion from considered to chosen.
Where this comes from
Armature ran 15,287 judged sessions with Claude Code, Codex, Cursor, Grok Build CLI and Muse Code inside 110 realistic codebases, and published every run. The numbers on this page come from that work.