CV3-Eval
Only in system cards
Text-to-speech models clone voices from in-the-wild reference audio across languages, dialects and emotions. Scored by ASR error rate, speaker similarity and DNSMOS audio quality.
Released with CosyVoice 3. Objective subsets cover multilingual, cross-lingual and emotion cloning, and three subsets are for human rating. Lower error rate is better.
Made by Alibaba Tongyi Lab (FunAudioLLM, CosyVoice team) Released May 2025 Speech recognition and translation All tasks public Last in a system card Apr 2026
Last model added Apr 2026
- Level
- Everyday Most adults, without training
- Scored
- Checked automatically A program checks the result against an answer key, unit tests or the expected final state.
- Answers
- Open-ended Free-form text, documents, designs or media judged as a whole.
2
System cards report it, from 1 lab
No scores here yet
No lab, leaderboard or Epoch AI run has reported a score for CV3-Eval yet.
Labs report it only in system cards
We read the headline results of 479 launch posts from 51 labs, and none of them list this benchmark. Some system cards do, below.
2 system cards report it, from 1 lab
Besides launch posts, we read the system cards, model cards and technical reports labs publish with a release. They report far more, including safety and frontier-risk tests.
| Date | Document | Score | As the document writes it | Section |
|---|---|---|---|---|
| 17 Apr 2026 |  Qwen3.5-Omni-Plus technical report | Cross-Lingual benchmark mixed error rate, 12 pairs, no overall (Table 11): en-zh 4.86, ja-zh 3.55, ko-zh 0.84, zh-en 2.18, ja-en 2.18, ko-en 2.51, zh-ja 5.92, en-ja 5.12, ko-ja 2.16, zh-ko 4.03, en-ko 3.72, ja-ko 5.12 | Capabilities | |
| 22 Sep 2025 | Qwen3-Omni-30B-A3B technical report | CosyVoice3 Cross-Lingual Test Set, 12 directions, WER from 0.99 (ko-to-zh) to 8.29 (zh-to-ja), no overall score (Table 15) | Capabilities |
More in Audio and video
- Video-MMMU In use 300 expert-level lecture videos with questions testing perception, comprehension and adaptation of knowledge. Accuracy. Qwen 3.8 Max 88.7%
- LVBench In use Hours-long video understanding with multiple-choice questions on reasoning, grounding and summarization.
Gemini 4 Argon 91.7% - MMVU In use 3,000 expert-annotated questions on videos across 27 disciplines. Multiple-choice and open-ended accuracy. Qwen 3.8 Max 82.4%
- MLVU In use Multi-task long video understanding (minutes to hours) with multiple-choice and generation tasks. Accuracy. Qwen 3.8 Max 90.8%
- VoiceBench In use Spoken instructions with speaker, environment and content variation. Voice assistant responses scored by GPT judge or rules. Qwen3.5-Omni-Plus 93.1%
- TVBench In use Models answer multiple-choice questions on 10 temporal video tasks, such as action counting and ordering, that static frames cannot solve. Scored by accuracy. Qwen 3.8 Max 81.9%