Voxtral 3 Release - Diarization - Overall: leaderboard
Voxtral 3 release evaluation (2026-10-20): exact chart marks retain model, series and score. FLEURS 45 macro-averages WER, using CER for Japanese, Korean, Thai and Chinese; language forced/inferred runs stay separate. Diarization averages cpWER over AMI-IHM, AMI-SDM, Switchboard, CallHome and AISHELL-4 with 30-minute clips. Context-bias recall uses Earnings22. Realtime latency configurations remain distinct. TTS tests retain their release-specific populations and judge; chart x-axis prices are never scores. cpWER (%).
Metric: cpWER (%). Source: mistral.ai. Saturation forecast: Rough model projection: around 2026. 7 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Voxtral Small Transcribe 3 | 18.4 | |
| 2 | Voxtral Mini Transcribe 3 | 18.6 | |
| 3 | Pyannote Orchestrator (Precision 3) | 19 | |
| 4 | Microsoft AI Transcribe 2 | 20.3 | |
| 5 | Scribe v2 | 23 | |
| 6 | Voxtral Mini Transcribe 2 | 30.9 | |
| 7 | Gemini 3.5 Transcribe | 38.4 |
Interactive version: theaggregate.ai/benchmark?slug=voxtral-3-release-diarization-overall · How It Works · Data refreshed daily, snapshot 2026-10-21.