# Phonic-1 launch evaluation: Voice Benchmark Profile

> Phonic’s launch table puts Phonic-1 (high) ahead of GPT-Live-1, Grok Voice 3.0 and Gemini 3.8 Live Extended Thinking on a speech-to-speech index (87.1), τ³-Voice task success (79.9%), multilingual τ³-Voice (83.2%) and Cekura’s live-call reliability (90.2%), with 0.61 s to first audio.

- Scope: Speech-to-speech index; τ³-Voice retail, airline and telecom task success; time to first audio; Big Bench Audio spoken reasoning; cost per hour of input audio; Sierra multilingual full-duplex τ³-Voice; Cekura S2S live-call reliability; Podonos blind listener preference
- Measurement lanes: Spoken reasoning, Task completion, Latency
- Primary metric: Index score and success rates (higher is better); time to first audio in seconds and cost per hour (lower is better)
- Available evidence: Exact values in the launch post’s table image and chart labels
- Owner: Phonic
- Source snapshots refreshed: 2026-10-28

- Provider report retrieved: 2026-10-29

## Launch comparison

Values as printed in Phonic’s launch table. Index and Big Bench Audio are scores out of 100; τ³-Voice and Cekura are success rates in percent; latency is time to first audio in seconds and cost is US dollars per hour of input audio (both lower is better). A dash means Phonic did not report the cell.

| Model | S2S index | τ³-Voice overall | Retail | Airline | Telecom | First audio (s) | Big Bench Audio | Cost / hour | Multilingual τ³-Voice | Cekura S2S pass³ |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| [Phonic-1 (high)](/models/phonic-1) | 87.1 | 79.9 | 72.8 | 78.8 | 88.3 | 0.61 | 98.9 | $4.20 | 83.2 | 90.2 |
| [GPT-Live-1 (Astra, medium)](/models/gpt-live-1) | 83.2 | 74.5 | 72.5 | 76.7 | 74.3 | 1.34 | 90.1 | $5.83 | 79.9 | 75.6 |
| [Grok Voice 3.0](/models/grok-voice-3-0) | 86.9 | 71.6 | 66.1 | 69.3 | 79.5 | 0.81 | 98.5 | $4.80 | — | 81.7 |
| [Gemini 3.8 Live Extended Thinking (high)](/models/gemini-3-8-live-extended-thinking) | 82.6 | 68.6 | 50.0 | 72.0 | 83.9 | 1.35 | 97.7 | $3.50 | 68.5 | 52.4 |
| Cascade (STT + GPT-4.1 + TTS) | — | 31.2 | 28.9 | 48.0 | 16.7 | — | — | — | — | 82.9 |

## Blind listener preference

Podonos blind pairwise study run for Phonic. Shares of votes for each side; the remainder were ties.

| Comparison | Phonic-1 preferred | Other preferred |
| --- | --- | --- |
| [Phonic-1 vs GPT-Live-1](/models/gpt-live-1) | 61.5% | 32.0% |
| [Phonic-1 vs Grok Voice 3.0](/models/grok-voice-3-0) | 66.5% | 26.5% |
| Phonic-1 vs Eleven v4 Turbo | 78.0% | 14.0% |
| Phonic-1 vs human voice actors | 32.0% | 57.0% |

## Interpretation limit

Phonic selected the competitors, settings and figures. It attributes the index, τ³-Voice, latency, Big Bench Audio and cost rows to Artificial Analysis, the multilingual τ³-Voice row to Sierra and the S2S row to Cekura, all dated October 29, 2026; those evaluators’ own pages were not re-checked for every cell, and the third-party figures are not licensed here for Data API redistribution. The Cekura row is pass³ reliability, which matches Cekura’s public board. GPT-Live-1 runs with GPT-6 Astra at medium effort in the Artificial Analysis rows but with GPT-6 Sol at low effort on Cekura. The cascade uses Deepgram Nova-3, GPT-4.1 and Deepgram Aura-1 for τ³-Voice (run by Sierra) and Deepgram Flux, GPT-4.1 and ElevenLabs Flash v2.5 for Cekura. The listener-preference study was run by Podonos for Phonic; the post’s prose rounds the human win rate to about 60% while the chart shows 57.0%. These results do not enter text-model rankings.

## Primary sources

- [Owner page](https://phonic.ai/blog/phonic-1)
- [Launch post](https://phonic.ai/blog/phonic-1)
- [Launch table image](https://cdn.prod.website-files.com/6a28062dd147f554ba12c01a/6ae35901aabe132393ac2b36_6ae358c0d6d8c31c55bdcc15_phonic-1-benchmarks-table-v2.png)
- [Pricing](https://phonic.ai/pricing)
- [Documentation](https://docs.phonic.ai/docs/get-started/overview)
- [Supported languages](https://docs.phonic.ai/docs/build/agents/supported_languages)
- [Cekura S2S leaderboard](https://benchmarks.cekura.ai/speech-to-speech)

Canonical page: https://benchlm.ai/voice-benchmarks/phonic-1-launch-evaluation