# Voice Arena launches a multilingual speech recognition benchmark with five-language test set

> Original title: A model being great at US English says little about how it ranks in other languages like Brazilian Portuguese.

- Source: Elvis Saravia
- Published: 2026-11-05T20:24:51.000Z
- Bad Influence: https://badinfluence.news/items/nyd6dikrtzf30ni4ognsk3ho2
- Original: https://x.com/omarsar0/status/2118439419787030983

## Summary

Voice Arena has launched a speech recognition benchmark covering every use case in every language, starting with the Monsoon Conversational ASR Test Set of two-person conversations in five languages. The post says a model's strong US English results say little about its ranking in other languages such as Brazilian Portuguese. Leaderboard and public test sets are available on Voice Arena.

## Post

A model being great at US English says little about how it ranks in other languages like Brazilian Portuguese.

These benchmark efforts matter a lot for voice.

The per-use-case benchmark is also ideal for properly measuring voice agents' effectiveness and robustness in certain languages.

## Quoted post @shobhitbanga

> Drop 3/15: Introducing the Speech Recognition Benchmark on @voicearena_ai.
> 
> One benchmark for every use case of speech recognition, in every language. Tested on real conversations.
> 
> Dataset 1 is live: the Monsoon Conversational ASR Test Set, two-person conversations in 5 languages.
> 
> Leaderboard and public test sets at Voice Arena.

https://x.com/shobhitbanga/status/2118438023675384079