# Artificial Analysis ranks SOV-Transcribe-1 top of open-weights speech models

> Original title: SOV-Transcribe-1's 2.3% word error rate puts it 0.5 points ahead of the next open weights models, @MistralAI's Voxtral Small and @nvidia ...

- Source: Artificial Analysis
- Published: 2026-11-12T16:30:50.000Z
- Bad Influence: https://badinfluence.news/items/jjsrkjjm7cnnoq5f2gi4nnw1w
- Original: https://x.com/ArtificialAnlys/status/2120917245870452840

## Summary

Artificial Analysis reports that SOV-Transcribe-1 has a 2.3% word error rate, 0.5 points ahead of the next open-weights models, Mistral's Voxtral Small and Nvidia's Nemotron 3.5 Transcribe, both at 2.8%.

## Post

SOV-Transcribe-1's 2.3% word error rate puts it 0.5 points ahead of the next open weights models, @MistralAI's Voxtral Small and @nvidia 's Nemotron 3.5 Transcribe, both at 2.8%

![](https://badinfluence.news/api/img-proxy?u=https%3A%2F%2Fpbs.twimg.com%2Fmedia%2FHW8CL0WbsAA2SBM.jpg&mode=thumb&exp=1794787200&sig=0e848f71923bfab9)