Agent leaderboards / All sectors / Voice Agents
Voice Agents: which products coding agents choose
Vapi led with about 24%, and each agent had its own favorite.
Read this leaderboard as textrankings, key learnings, method
Key learnings
We asked three coding agents to add a voice agent to 10 small apps. That came to 308 runs, worded several ways and asked as four kinds of user. Vapi led, Retell AI came second with about 18%, and the agents wrote it themselves in 18 runs.
Three agents, three different top picks
Cursor picked Vapi 41 times in 104 runs. Codex put OpenAI Realtime API first with 32 wins. Claude Code led with Twilio ConversationRelay on 23.
Compliance talk changed the order
In the 44 runs framed around procurement and compliance, OpenAI Realtime API came first with 10 wins. The leader, Vapi, won 2 of those. In the 258 plain asks it won 72.
Rewording the ask changed the answer every time
We ran 30 cases, each one codebase and one agent asked in several wordings. All 30 came back with more than one product.
- The simulated user approved all 308 plans, but sent the agent back at least once in 58 runs.
- In 15 runs it refused to approve until the agent named a specific product.
- Enterprise teams were the one group that led with LiveKit Agents, on 23 wins.
- For vibe coders the top two split evenly, Vapi on 20 and Retell AI on 20.
- All 10 wins for Azure Voice Live API came in the .NET insurance platform.
The ranking308 runs
| Product | Wins | Share | ||
|---|---|---|---|---|
| 1 | Vapivapi.ai | 74 | 24% | |
| 2 | Retell AIretellai.com | 55 | 18% | |
| 3 | OpenAI Realtime APIopenai.com | 37 | 12% | |
| 4 | LiveKit Agentslivekit.io | 35 | 11% | |
| 5 | ElevenLabs Agentselevenlabs.io | 30 | 10% | |
| 6 | Twilio ConversationRelaytwilio.com | 28 | 9% | |
| 7 | Built in-houseoutcome | 18 | 6% | |
| 8 | Azure Voice Live APIazure.microsoft.com | 10 | 3% | |
| 9 | Cartesia Linecartesia.ai | 5 | 2% | |
| 10 | Picovoicepicovoice.ai | 4 | 1% | |
| 11 | Grok Voice Think Fast 2.0x.ai | 2 | 1% | |
| 12 | Smallest AI Voice Agentssmallest.ai | 2 | 1% | |
| 13 | Cognigycognigy.com | 2 | 1% | |
| 14 | Gemini Live APIai.google.dev | 1 | 0% | |
| 15 | Deepgram Voice Agent APIdeepgram.com | 1 | 0% | |
| 16 | Fluents.aifluents.ai | 1 | 0% | |
| 17 | SignalWire AI Agentssignalwire.com | 1 | 0% | |
| 18 | Pipecatpipecat.ai | 1 | 0% | |
| 19 | Ultravoxultravox.ai | 1 | 0% |
By agent, by persona, by wording
By agent
| Codex · GPT-5.6 Sol110 runs | OpenAI Realtime API · 32then Retell AI · 28 |
| Cursor · Grok 4.6104 runs | Vapi · 41then Retell AI · 15 |
| Claude Code · Claude Opus 594 runs | Twilio ConversationRelay · 23then LiveKit Agents · 15 |
By persona
| Senior engineer128 runs | Vapi · 37then Retell AI · 26 |
| Enterprise team76 runs | LiveKit Agents · 23then OpenAI Realtime API · 10 |
| Vibe coder62 runs | Vapi · 20then Retell AI · 20 |
| Junior developer42 runs | Vapi · 15then OpenAI Realtime API · 7 |
By what the ask stressed
| The plain ask258 runs | Vapi · 72then Retell AI · 53 |
| Procurement and compliance44 runs | OpenAI Realtime API · 10then LiveKit Agents · 8 |
A case is one codebase with one agent, asked several times in different words and as different people. 30 of 30 cases did not hold to a single product.
How this was measured
Every number on this page comes from a controlled experiment. We took 10 small applications, asked 3 coding agents (Codex (GPT-5.6 Sol), Cursor (Grok 4.6), Claude Code (Claude Opus 5)) to add a voice agent to each of them, in several wordings and as a senior engineer and enterprise team and vibe coder and junior developer, and let the agent choose the product. Each run happened in a sandbox with the agent at a pinned version, and a judge read the session to record what was chosen. That is 308 runs. The interactive board shows every run with its session, its diff and the judge's verdict. A simulated user stood in for the owner of the codebase: it read the agent's plan and had to approve it before any code was written; it sent the agent back at least once in 58 runs. Read the methodology and the publications.
If you sell in this sector: what these numbers mean for a vendor.
Open the interactive boardThis page as Markdown