Model rankings
1278 models · 5 boards · 2 sources
Best voice
Best open model
Best from China
Top three by Score
Fun-Realtime-TTSAlibaba1,224
Gemini 3.1 Flash TTSGoogle1,222
Realtime TTS-2 - Research PreviewInworld1,212
Top three open models
Fish Audio S2 ProFish Audio · #20 overall1,117
Step Audio EditX (Mar 2026)StepFun · #22 overall1,115
Voxtral TTSMistral · #34 overall1,081
This week's changes
glm-5.2 (max)Coding · #2New
GLM-5.2 (max)Intelligence · #6New
seed-2.1-pro-previewCoding · #6New
Lightning V3.1 Pro TTS (Jun 2026)Speech · #11New
kimi-k2.7-codeCoding · #17New
| Rank | Change | Model | Score | 95% interval |
|---|---|---|---|---|
| 1 | — | Fun-Realtime-TTSClosedAlibaba | 1,224 | ±16 |
| 2 | — | StepAudio 2.5 TTSClosedStepFun | 1,181 | ±16 |
| 3 | — | Speech 2.8 HDClosedMiniMax | 1,174 | ±12 |
| 4 | — | Step TTS 2 (Mar 2026)ClosedStepFun | 1,159 | ±14 |
| 5 | — | Speech 2.8 TurboClosedMiniMax | 1,158 | ±12 |
| 6 | — | Speech 2.6 TurboClosedMiniMax | 1,141 | ±11 |
| 7 | — | Speech 2.6 HDClosedMiniMax | 1,141 | ±12 |
| 8 | — | Speech-02-HDClosedMiniMax | 1,109 | ±11 |
| 9 | — | Speech-02-TurboClosedMiniMax | 1,094 | ±12 |
| 10 | — | MiMo-V2.5-TTSClosedXiaomi | 1,081 | ±14 |
| 11 | — | T2A-01-HDClosedMiniMax | 1,068 | ±11 |
| 12 | — | T2A-01-TurboClosedMiniMax | 1,030 | ±11 |
| 13 | — | MiMo-V2-TTSClosedXiaomi | 1,019 | ±14 |
| 14 | — | Qwen3 TTS FlashClosedAlibaba | 934 | ±14 |
| 15 | — | Qwen3 TTSClosedAlibaba | 923 | ±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