Model rankings
1510 models · 5 boards · 2 sources
Best voice
Best open model
Best from China
Top three open models
Breeze TTS 2BreezeBlue · #10 overall1,216
Fish Audio S2 ProFish Audio · #32 overall1,117
Step Audio EditX (Mar 2026)StepFun · #39 overall1,095
This week's changes
Claude Sonnet 5.5 (Max, Default Fallback)Intelligence · #2New
Utopai XVideo · #2New
Dreamina Seedance 2.5Video · #3New
Gemini 4 Argon (High)Intelligence · #5New
MiniMax H3 MaxVideo · #5New
| Rank | Change | Model | Score | 95% interval |
|---|---|---|---|---|
| 1 | — | Qwen-Audio-3.1-TTS-PlusClosedAlibaba | 1,292 | ±18 |
| 2 | — | Qwen-Audio-3.0-TTS-PlusClosedAlibaba | 1,261 | ±15 |
| 3 | — | StepAudio 2.5 TTS (Aug 2026)ClosedStepFun | 1,210 | ±15 |
| 4 | — | Speech 2.8 HDClosedMiniMax | 1,173 | ±11 |
| 5 | — | Speech 2.8 TurboClosedMiniMax | 1,153 | ±11 |
| 6 | — | Step TTS 2 (Mar 2026)ClosedStepFun | 1,134 | ±12 |
| 7 | — | Speech 2.6 HDClosedMiniMax | 1,128 | ±11 |
| 8 | — | Speech 2.6 TurboClosedMiniMax | 1,124 | ±11 |
| 9 | — | Speech-02-HDClosedMiniMax | 1,114 | ±11 |
| 10 | — | Step Audio EditX (Mar 2026)OpenStepFun | 1,095 | ±13 |
| 11 | — | Speech-02-TurboClosedMiniMax | 1,090 | ±12 |
| 12 | — | T2A-01-HDClosedMiniMax | 1,066 | ±11 |
| 13 | — | MiMo-V2.5-TTSClosedXiaomi | 1,055 | ±13 |
| 14 | — | T2A-01-TurboClosedMiniMax | 1,031 | ±11 |
| 15 | — | MiMo-V2-TTSClosedXiaomi | 1,024 | ±14 |
| 16 | — | Qwen3 TTS FlashClosedAlibaba | 944 | ±14 |
| 17 | — | Qwen3 TTSClosedAlibaba | 932 | ±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