Skip to content

Benchmark

Voice Code Bench · Faithful clips

Scores are percentages. Higher is better.

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

Score distribution

79.7%
Mean
79.7%
Median
0%
Std dev
79.7%
10th percentile
79.7%
90th percentile
79.7%
Min

Leaderboard

#ModelScore
1Voxtral Mini TTS 3.0Voxtral 3 official release chart · BeSimple AI · 300 English prompts · two voices · Gemini 3.8 Flash judge· Reported by Mistral AI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.79.7%

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.