Kyutai
We track 3 benchmarks that Kyutai made or helped make. Its models are on its lab page.
0 in use 1 with public code 0 with a leaderboard here
Benchmarks
| Name | Kind | Released | Best score | Status |
|---|---|---|---|---|
| Audio-NTREX-4L Speech translation models translate long-form French, Spanish, Portuguese and German audio into English. | Translation | Feb 2026 | Not in cards | |
| HaluEvalAudio 1000 Audio language models answer spoken questions against supplied knowledge and reference answers. | Hallucination rates | Mar 2026 | Not in cards | |
| KairosQA Models answer questions about facts that changed over time, with each item tied to a time period. | Language reasoning | Feb 2026 | Not in cards |