Introducing Grok Voice 3.0 (xAI news) Oct 14, 2026
Grok Voice 3.0
Grok Voice 3.0 ranks first on 4 of the 6 benchmarks with five or more models scored.
9
Benchmarks with a score
4
Ranked first, out of five or more models
4
In the top three
xAI Oct 2026
Grok Voice 3.0
Closed weights Flagship
No Epoch Capabilities Index score yet
- Cekura Agent Performance 81.7% #1 /5
- Cekura Turn Bench 74.5% #4 /5
- Big Bench Audio 98.5% #1 /7
Where it ranks
Its best score on each benchmark, and where that ranks among every model with a score there. We rank each model once, at its best setting.
Vision, audio and robotics
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| EVA-Bench | 0.74 | #1 of 8 | Official leaderboard | |
| Big Bench Audio | 98.5% | #1 of 7 | Lab model card | |
| Audio Arena | 85.7 | #1 of 6 | Official leaderboard | |
| Cekura Agent Performance | 81.7% | #1 of 5 | Official leaderboard | |
| vCX Benchmark | 91.2% | #9 of 42 | Official leaderboard | |
| τ-Voice | 71.6% | #1 of 4 | Lab model card | |
| Speech-to-Speech Index | 86.9 | #1 of 2 | Lab model card | |
| Cekura Turn Bench | 74.5% | #4 of 5 | Official leaderboard | |
| Speech Agent Arena | 1,070 | #1 of 1 | Lab model card |
Its launch post
The benchmarks the lab chose to headline, with the scores it gave.