From the experiment

Do coding agents recommend ElevenLabs Agents?

ElevenLabs Agents was chosen in 10% of 308 judged voice agents sessions, ranking fifth. Measured with Claude Code, Codex and Cursor.

Published September 3, 2026 Read as Markdown

ElevenLabs Agents was chosen in 10% of 308 judged voice agents sessions, ranking fifth. It was also raised as a candidate in 72 further sessions without being chosen.

This page reports what happened when Claude Code, Codex and Cursor had to solve a problem in voice agents inside a realistic codebase. Not what a chat assistant says about ElevenLabs Agents. What an agent actually installed.

The numbers

CategoryVoice agents
Sessions in the category308
Sessions where ElevenLabs Agents was chosen30
Install share10%
Rank in category5 of 18
Codebases it won in5
Raised as a candidate, not chosen72
Chosen when considered29%
Siteelevenlabs.io

By agent

The three agents land within 11 points of each other on ElevenLabs Agents, which is closer than most products in this experiment manage.

AgentSessionsChose ElevenLabs AgentsShare
Claude Code941516%
Codex110109%
Cursor10455%

By who was asking

ElevenLabs Agents does much better with one kind of buyer than another. It won 21% of sessions asked as vibe coder and 0% of those asked as junior developer.

Who is askingSessionsChose ElevenLabs AgentsShare
Vibe coder621321%
Junior developer4200%
Senior engineer128129%
Enterprise team7657%

What ElevenLabs Agents was up against

The full ranking in voice agents, from the same sessions:

#ProductRuns wonShare
1Vapi7424%
2Retell AI5518%
3OpenAI Realtime API3712%
4LiveKit Agents3511%
5ElevenLabs Agents (this page)3010%
6Twilio ConversationRelay289%
7Built in-house (no product adopted)186%
8Azure Voice Live API103%

What this means

ElevenLabs Agents was raised in 72 sessions and chosen in 30. 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 308 sessions in voice agents 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 voice agents run can be replayed on the board.

If you work on ElevenLabs Agents: 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 ElevenLabs Agents?

Yes. ElevenLabs Agents was chosen in 30 of the 308 judged sessions in voice agents, a 10% install share, ranking fifth in its category.

Does Claude Code recommend ElevenLabs Agents?

In 15 of the 94 sessions in voice agents run with Claude Code, which is 16%.

Do different coding agents treat ElevenLabs Agents differently?

Yes, and by a wide margin. Claude Code chose it in 16% of its runs and Cursor in 5%.

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 ElevenLabs Agents considered but not chosen?

It was raised as a candidate in 72 sessions without being chosen, and chosen in 30. That is a 29% 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.

Read next

All library pages