# Grok Voice 3.0 Benchmark Scores & Performance

> Grok Voice 3.0 has xAI voice launch evaluation results. Voice evidence is display-only and does not produce a text-model score.

Canonical page: https://benchlm.ai/models/grok-voice-3-0

Last updated: October 14, 2026

## Model Details

| Property | Value |
|----------|-------|
| Creator | xAI |
| Source Type | Proprietary |
| Reasoning Type | Non-Reasoning |
| Context Window | N/A |
| Official model card | [xAI model documentation](https://docs.x.ai/developers/model-capabilities/audio/voice-agent) |
| Overall Score | Not scored (voice evidence only) |
| Overall Rank | Unranked |

## Family & Coverage

- Family: Grok Voice 3.0
- Variant: base
- Benchmarks covered: 0 of 629
- Coverage note: Speech and voice results appear below; no weighted text-model benchmark rows are stored.

## Speech and voice evidence

[Grok Voice 3.0 launch evaluation](/voice-benchmarks/grok-voice-3-launch-evaluation)

The 74% figure is a provider-reported EVA-Bench claim, not an independently refreshed owner result here. Voice results stay separate from weighted text-model scores.

| Metric | Result |
| --- | --- |
| EVA-Bench accuracy (xAI launch claim) | 74% |

xAI launch claim retrieved October 14, 2026. Independent speech benchmark observations are retained separately in the internal source snapshot.

- [Evaluation source](https://x.ai/news/grok-voice-3)

Available in the Voice Agent API as `grok-voice-3.0`. The `grok-voice-latest` alias now points to this release; xAI documents Grok Voice 2.0 as deprecated. The existing WebSocket endpoint, session parameters, and events are unchanged. Sessions support audio and text, custom voices, function calls, search, and MCP tools.

## Other xAI Models

- [Grok 4.6](/models/grok-4-6) - Score: 66.95
- [Grok 4.5](/models/grok-4-5) - Score: 63.26
- [Grok 4.20](/models/grok-4-20-beta) - Score: 57.65
- [Grok 4.3](/models/grok-4-3) - Score: 53.07
- [Grok 4](/models/grok-4) - Score: 51.78
- [Grok 4.1 Fast (Reasoning)](/models/grok-4-1-fast-reasoning) - Score: 45.83
- [Grok 3 Mini](/models/grok-3-mini) - Score: 44.23
- [Grok 4 Fast (Reasoning)](/models/grok-4-fast-reasoning) - Score: 43.48
- [Grok 3 [Beta]](/models/grok-3-beta) - Score: 41.04
- [Grok 4.1 Fast](/models/grok-4-1-fast) - Score: 36.49
- [Grok Code Fast 1](/models/grok-code-fast-1) - Score: 34.13
- [Grok 4.7](/models/grok-4-7) - Score: not computed
- [Grok 2](/models/grok-2) - Score: not computed
- [Grok 2 mini](/models/grok-2-mini) - Score: not computed
- [Grok 4.1](/models/grok-4-1) - Score: not computed
- [Grok Voice Transcribe 2.0](/models/grok-voice-transcribe-2) - Score: not computed
- [Grok Voice Think Fast 2.0](/models/grok-voice-think-fast-2-0) - Score: not computed
- [Grok Build 0.1](/models/grok-build-0-1) - Score: not computed
- [Grok Voice Think Fast 1.0](/models/grok-voice-think-fast-1-0) - Score: not computed
- [Grok TTS](/models/grok-tts) - Score: not computed
- [Grok 4.20 Multi-agent](/models/grok-4-20-multi-agent-beta) - Score: not computed
- [Grok Realtime](/models/grok-realtime) - Score: not computed