Skip to main content

Benchmark profile

VoxPopuli-Cleaned-AA Word Error Rate (VoxPopuli WER)

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

Data verified

Benchmark score on VoxPopuli WER — July 23, 2026

BenchLM mirrors the published score view for VoxPopuli WER. Interfaze Beta leads the public snapshot at 2.4%. BenchLM does not use these results to rank models overall.

1 modelMultimodal & GroundedCurrentDisplay onlyUpdated July 23, 2026

Benchmark score table (1 model)

Score
1
Interfaze BetaInterfaze · Closed
2.4%

About VoxPopuli WER

Year

2026

Tasks

Speech-to-text transcription

Format

Word error rate

Difficulty

Audio speech recognition

VoxPopuli-Cleaned-AA measures transcription quality on multilingual European Parliament speech using Whisper-style text normalization. BenchLM stores Interfaze's WER as a display-only multimodal and audio row.

BenchLM freshness & provenance

Version

VoxPopuli WER 2026

Refresh cadence

Quarterly

Staleness state

Current

Question availability

Public benchmark set

CurrentDisplay only

BenchLM uses freshness metadata to decide whether a benchmark should still be treated as a strong differentiator, a benchmark to watch, or a display-only reference. For the full scoring policy, see the BenchLM methodology page.

FAQ

What does VoxPopuli WER measure?

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

Which model scores highest on VoxPopuli WER?

Interfaze Beta by Interfaze currently leads with a score of 2.4% on VoxPopuli WER.

How many models are evaluated on VoxPopuli WER?

1 AI models have been evaluated on VoxPopuli WER on BenchLM.

Last updated: July 23, 2026 · BenchLM version VoxPopuli WER 2026

Choose a model with this week’s evidence

Join 2,000+ readers for ranking moves, pricing changes, and the claims that still need proof.

One email each week. Unsubscribe anytime.