Model rankings
866 models · 5 boards · 2 sources
Best voice
Best open model
Best from China
Top three by Score
Eleven v4ElevenLabs1,334
Eleven v4 TurboElevenLabs1,331
Qwen-Audio-3.1-TTS-PlusAlibaba1,301
Top three open models
Fish Audio Drama 3Fish Audio · #6 overall1,272
Fish Audio Drama 3 PreviewFish Audio · #12 overall1,239
Breeze TTS 2BreezeBlue · #13 overall1,226
This week's changes
Gemini 4 Carbon (High)Intelligence · #1New
GPT-6.1 Terra (Max)Intelligence · #6New
Fish Audio Drama 3Speech · #6New
P-Video-2-ProVideo · #11New
AssemblyAI-TTS-1Speech · #14New
| Rank | Change | Model | Score | 95% interval |
|---|---|---|---|---|
| 1 | — | Qwen-Audio-3.1-TTS-PlusClosedAlibaba | 1,301 | ±15 |
| 2 | — | Qwen-Audio-3.0-TTS-PlusClosedAlibaba | 1,266 | ±13 |
| 3 | — | StepAudio 2.5 TTS (Aug 2026)ClosedStepFun | 1,210 | ±13 |
| 4 | — | Ming-3.0-ttsOpenAnt Group | 1,189 | ±13 |
| 5 | — | Speech 2.8 HDClosedMiniMax | 1,173 | ±10 |
| 6 | — | Speech 2.8 TurboClosedMiniMax | 1,151 | ±10 |
| 7 | — | Step TTS 2 (Mar 2026)ClosedStepFun | 1,136 | ±11 |
| 8 | — | Speech 2.6 HDClosedMiniMax | 1,125 | ±11 |
| 9 | — | Speech 2.6 TurboClosedMiniMax | 1,120 | ±10 |
| 10 | — | Speech-02-HDClosedMiniMax | 1,106 | ±11 |
| 11 | — | Step Audio EditX (Mar 2026)OpenStepFun | 1,097 | ±12 |
| 12 | — | Speech-02-TurboClosedMiniMax | 1,090 | ±11 |
| 13 | — | T2A-01-HDClosedMiniMax | 1,072 | ±11 |
| 14 | — | MiMo-V2.5-TTSClosedXiaomi | 1,052 | ±12 |
| 15 | — | T2A-01-TurboClosedMiniMax | 1,027 | ±11 |
| 16 | — | Qwen3 TTS FlashClosedAlibaba | 939 | ±14 |
| 17 | — | Qwen3 TTSClosedAlibaba | 929 | ±13 |
Intelligence over time
Gained most · Anthropic +57.2Highest now · Anthropic 64.6Gap between highest and lowest 18.1 ptsTime range Nov 2025 – Nov 2026
64.6Anthropic60.0Google56.9OpenAI50.1Meta46.5Kimi