Benchmark
Artificial Analysis Speech to Speech Quality Index
Scores are percentages. Higher is better.
- Models measured
- 3
- Scores recorded
- 4
- Sources
- 1
- IQ weight
- No weight published
Score distribution
- 80%
- Mean
- 82.6%
- Median
- 5%
- Std dev
- 74.5%
- 10th percentile
- 86.9%
- 90th percentile
- 74.5%
- Min
Leaderboard
| # | Model | Score |
|---|---|---|
| 1 | Grok Voice 3.0October 13 release table · Artificial Analysis Speech to Speech Index· Reported by SpaceXAI, Artificial Analysis· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 86.9% |
| 2 | Gemini 3.8 Live Extended Thinkinghigh thinking · Gemini API · Artificial Analysis composite· Reported by Google DeepMind, Google· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 82.6% |
| 3 | Gemini 3.8 LiveGemini API · Artificial Analysis composite · thinking level not printed on chart· Reported by Google DeepMind· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 76% |
| 4 | Gemini 3.8 LiveArtificial Analysis live leaderboard · October 24 snapshot · index methodology as displayed by maintainer· Reported by Artificial Analysis· via BenchBoard docs | 74.5% |