language benchmark
CoVoST 2 is a large-scale multilingual speech translation corpus derived from Common Voice, covering translations from 21 languages into English and from English into 15 languages. The dataset contains 2,880 hours of speech with 78K speakers for speech translation research.
Updated Aug 11, 2026
Higher score ranks better on this benchmark.
| 01 | AM | 40.7% | 100.0% | 4 | C | |
| 02 | GO | 39.2% | 66.7% | 4 | C | |
| 03 | GO | 38.5% | 33.3% | 4 | C | |
| 04 | GO | 38.4% | 0.0% | 4 | C |
A closer view of the leading scores on this benchmark.
The leading models and scores on this benchmark.
What CoVoST2 measures and how its scores work.
CoVoST 2 is a large-scale multilingual speech translation corpus derived from Common Voice, covering translations from 21 languages into English and from English into 15 languages. The dataset contains 2,880 hours of speech with 78K speakers for speech translation research.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
Benchmark scores retain their original unit. Overall score eligibility is shown separately.
Common questions about CoVoST2.
Nova 2 Omni is currently ranked first with 40.7%.
CoVoST 2 is a large-scale multilingual speech translation corpus derived from Common Voice, covering translations from 21 languages into English and from English into 15 languages. The dataset contains 2,880 hours of speech with 78K speakers for speech translation research.
Yes. Higher values rank better for this benchmark.
4 model results are currently shown.
Yes. This benchmark can contribute to the current LLMBoard capability score.