Skip to main content
ModelScale

Multimodal & Grounded benchmark

VoxPopuli WER leaderboard

VoxPopuli-Cleaned-AA Word Error Rate. Every model the catalog carries a published VoxPopuli WER value for, ranked by that value.

CategoryMultimodal & Grounded
MeasureWord error rate
TasksSpeech-to-text transcription
DifficultyAudio speech recognition

A speech-recognition benchmark on the cleaned Artificial Analysis VoxPopuli subset, reported as word error rate where lower is better.

VoxPopuli WER ranking

1 model with a published VoxPopuli WER value, ordered by that value, highest first. Models the source has not scored on this benchmark are not listed — they are unmeasured, not last.

Models ranked by their published VoxPopuli-Cleaned-AA Word Error Rate value
RankModelProviderWord error rate
1INInterfaze BetaInterfaze2.4

Evidence key: Observed

Rows are ordered by the value VoxPopuli-Cleaned-AA published, highest first. The source does not state whether a higher value is the better result, so this page does not either: for a benchmark that measures a rate of failure, read the table from the bottom.

All leaderboards