Voxtral Small Transcribe 3 Takes #3 on STT Leaderboard at 2.1% WER, Edging Scribe v2
ArtificialAnlys · x · 2026-10-21
Artificial Analysis updated its non-streaming speech-to-text leaderboard: Voxtral Small Transcribe 3 ranks #3 with a 2.1% AA-WER Index, ahead of ElevenLabs Scribe v2 (2.2%) and Grok Voice Transcribe 2.0 (2.3%); Voxtral Mini Transcribe 3 lands #5 at 2.2%.
AA-WER v2.5 blends three datasets: AA-AgentTalk (50%), VoxPopuli-Cleaned-AA (25%), and Earnings22-Cleaned-AA (25%). Voxtral Small scores 1.7% on AgentTalk, 1.5% on VoxPopuli, and 3.6% on Earnings22. Charts cover full-model rankings and per-dataset breakdowns.
More from Models
- antirez on model upgrades: 4.0→4.1 knowledge transfers unless attention changes — teortaxesTex · 2026-10-21
- DeepSeek reportedly profits at $0.15/$0.60 off-peak pricing — the price Western labs must beat — arthurcolle · 2026-10-21
- SpecterOps Researchers Show Adversarial ML Evading EDR, LLMs Speeding Reverse Engineering — dyn___ · 2026-10-21
- Riemann-bench: frontier models jump from under 5% to over 70% in six months, NS and UGC solved — echen · 2026-10-21
- DeepSeek 4.1 Flash needs ~200 tok/s local decode speed to be competitive, says heavy user — antirez · 2026-10-21
- Space Bunny Alpha revealed as MiniMax M3.1 Flash: 1M context, budget-friendly coding — ZabihullahAtal · 2026-10-21