Skip to content

Benchmark

Expressive English TTS · Mean judge score

Higher scores are better.

Models measured
1
Scores recorded
1
Sources
1
IQ weight
No weight published

Score distribution

3.1
Mean
3.1
Median
0
Std dev
3.1
10th percentile
3.1
90th percentile
3.1
Min

Leaderboard

#ModelScore
1Voxtral Mini TTS 3.0Voxtral 3 official release chart · internal one_eval · 237 selected prompts / two voices · 1–5 judge scale · Gemini 3.8 Flash· Reported by Mistral AI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.3.1

Data credits: BenchBoard by SYuan03 (github.com/SYuan03/benchboard). MIT covers its code and data organization; no results licence is inferred. Numeric relays retain the original stating-source links.