Grok Voice 2.0 places in the top three on 4 benchmarks.
Closed weights Flagship
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.
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| τ-bench 2.0 | 71.4% | #2 of 3 | Official leaderboard |
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| Big Bench Audio | 97.2% | #2 of 7 | Lab model card | |
| τ-Voice | 62.5% | #3 of 7 | Official leaderboard | |
| EVA-Bench | 0.52 | #4 of 8 | Official leaderboard | |
| Audio Arena | 80.5 | #3 of 6 | Official leaderboard | |
| Cekura Agent Performance | 67.1% | #3 of 5 | Official leaderboard | |
| Cekura Turn Bench | 73.7% | #5 of 5 | Official leaderboard | |
| Speech-to-Speech Index | 82.9 | #2 of 2 | Lab model card |
Where the benchmark's own leaderboard, or Epoch AI's run, also has this model. Gaps mostly come from different harnesses, effort levels and task subsets. Every pair.
The benchmarks the lab chose to headline, with the scores it gave.