Do coding agents recommend Langfuse?
Langfuse is the most chosen eval tool, taking 34% of 288 judged evals sessions. Measured with Claude Code, Codex and Cursor.
Langfuse is the most chosen eval tool, taking 34% of 288 judged evals sessions. It was also raised as a candidate in 109 further sessions without being chosen.
This page reports what happened when Claude Code, Codex and Cursor had to solve a problem in evals inside a realistic codebase. Not what a chat assistant says about Langfuse. What an agent actually installed.
The numbers
| Category | Evals |
| Sessions in the category | 288 |
| Sessions where Langfuse was chosen | 97 |
| Install share | 34% |
| Rank in category | 1 of 9 |
| Codebases it won in | 2 |
| Raised as a candidate, not chosen | 109 |
| Chosen when considered | 47% |
| Site | langfuse.com |
By agent
The three agents land within 8 points of each other on Langfuse, which is closer than most products in this experiment manage.
| Agent | Sessions | Chose Langfuse | Share |
|---|---|---|---|
| Claude Code | 96 | 36 | 38% |
| Codex | 96 | 29 | 30% |
| Cursor | 96 | 32 | 33% |
By who was asking
Langfuse does much better with one kind of buyer than another. It won 42% of sessions asked as junior developer and 25% of those asked as senior engineer.
| Who is asking | Sessions | Chose Langfuse | Share |
|---|---|---|---|
| Junior developer | 145 | 61 | 42% |
| Senior engineer | 143 | 36 | 25% |
What Langfuse was up against
The full ranking in evals, from the same sessions:
| # | Product | Runs won | Share |
|---|---|---|---|
| 1 | Langfuse (this page) | 97 | 34% |
| 2 | Built in-house (no product adopted) | 84 | 29% |
| 3 | Promptfoo | 38 | 13% |
| 4 | Arize Phoenix | 23 | 8% |
| 5 | Braintrust | 18 | 6% |
| 6 | Inspect AI | 12 | 4% |
| 7 | LangSmith | 8 | 3% |
| 8 | Helicone | 6 | 2% |
What this means
Leading a category is a position to defend rather than a result to celebrate. In our data, leaders lose ground in exactly two situations: when the person asking is an enterprise buyer with procurement constraints, and when a competitor's documentation is easier for an agent to integrate correctly.
The defence is unglamorous. Keep the quickstart running. Keep the version current on the page. Keep the names aligned. Stay in the templates.
Where these numbers come from
The 288 sessions in evals 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 evals run can be replayed on the board.
If you work on Langfuse: 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 Langfuse?
Yes. Langfuse was chosen in 97 of the 288 judged sessions in evals, a 34% install share, ranking first in its category.
Does Claude Code recommend Langfuse?
In 36 of the 96 sessions in evals run with Claude Code, which is 38%.
Do different coding agents treat Langfuse differently?
Not much. The three agents chose it at similar rates, between 30% and 38% 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.
How often is Langfuse considered but not chosen?
It was raised as a candidate in 109 sessions without being chosen, and chosen in 97. That is a 47% conversion from considered to chosen.
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.