Skip to main content
ModelScale

external benchmark

VoiceCodeBench leaderboard

Vals VoiceCodeBench. Every model the catalog carries a published VoiceCodeBench value for, ranked by that value.

Categoryexternal
MeasureTask success rate
Tasks300 workplace speech clips with exact structured values
DifficultyStructured-value speech transcription

Tests whether speech-to-text models preserve exact structured values in English workplace audio.

No model in the catalog has a published VoiceCodeBench score.

The benchmark is defined by Vals VoiceCodeBench, but the catalog carries no value for it yet. An absent value is shown as absent here rather than as a zero.

All leaderboards