Ming-3.0-tts-0.5B model card Sep 22, 2026
- seed-tts-eval-zh WER ↓ 0.8
- German WER ↓ 0.365
Ming-3.0-tts-0.5B.
Open weights Small
Its best score on each benchmark, and where that ranks among every model with a score there. We rank each model once, at its best setting.
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| DRAMA-Eval | 2.55% | #1 of 2 | Official leaderboard | |
| Seed-TTS-eval | 0.80% | #2 of 2 lab numbers | Lab model card | |
| MiniMax TTS Multilingual Test Set | 0.36% | #1 of 1 lab number | Lab model card |
Independent runs cover 1 of its 3 benchmarks. For the other 2, we have only Ant Group's own number or a claim Epoch AI collected.
Sources: Official leaderboards, Epoch AI (CC BY 4.0) and labs’ model cards
The benchmarks the lab chose to headline, with the scores it gave.