Do coding agents recommend Helicone?
Helicone was chosen in 3% of 478 judged evals sessions, ranking sixth. Measured with Claude Code, Codex, Cursor, Grok Build CLI and Muse Code.
Helicone was chosen in 3% of 478 judged evals sessions, ranking sixth. It was also raised as a candidate in 194 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 Helicone. What an agent actually installed.
One thing to read first: every one of those wins came from a single codebase. That is a result about one repository rather than about evals in general, and the splits below cannot separate the two. Treat them as a description of that repository.
The numbers
| Category | Evals |
| Sessions in the category | 478 |
| Sessions where Helicone was chosen | 12 |
| Install share | 3% |
| Rank in category | 6 of 11 |
| Codebases it won in | 1 |
| Raised as a candidate, not chosen | 194 |
| Chosen when considered | 6% |
| Site | helicone.ai |
By agent
With 12 wins spread across 5 agents, the rates below are small numbers and a difference between them is not yet a finding. They are here because the direction is worth knowing, not because the gap is established.
| Agent | Sessions | Chose Helicone | Share |
|---|---|---|---|
| Claude Code | 120 | 0 | 0% |
| Codex | 144 | 6 | 4% |
| Cursor | 120 | 1 | 1% |
| Grok Build CLI | 22 | 0 | 0% |
| Muse Code | 72 | 5 | 7% |
By who was asking
Helicone performs similarly across the four kinds of buyer, from 2% to 3%. That is unusual: the category leader changed with the persona in 23 of the 31 categories we measured.
| Who is asking | Sessions | Chose Helicone | Share |
|---|---|---|---|
| Junior developer | 241 | 4 | 2% |
| Senior engineer | 237 | 8 | 3% |
What Helicone 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 | 23 | 5% |
| 6 | Inspect AI | 16 | 3% |
| 7 | Helicone (this page) | 12 | 3% |
| 8 | LangSmith | 9 | 2% |
What this means
This is an integration problem, not a presence problem. Agents raised Helicone in 194 sessions and chose it in 12, 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 15,051, 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 Helicone: 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 Helicone?
Yes. Helicone was chosen in 12 of the 478 judged sessions in evals, a 3% install share, ranking sixth in its category.
Does Claude Code recommend Helicone?
In 0 of the 120 sessions in evals run with Claude Code, which is 0%.
Do different coding agents treat Helicone differently?
Not much. Claude Code, Codex, Cursor and Muse Code chose it at similar rates, between 0% and 7% of their runs.
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 Helicone considered but not chosen?
It was raised as a candidate in 194 sessions without being chosen, and chosen in 12. That is a 6% 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.