Model rankings
1447 models · 5 boards · 2 sources
Best voice
Best open model
Best from China
Top three by Score
Sonic 3.6Cartesia1,283
Qwen-Audio-3.0-TTS-PlusAlibaba1,240
Simba 3.2SpeechifyAI1,240
Top three open models
Fish Audio S2 ProFish Audio · #25 overall1,126
Step Audio EditX (Mar 2026)StepFun · #30 overall1,107
Voxtral TTSMistral · #40 overall1,079
This week's changes
hy4-previewCoding · #5New
GLM-5.3 (max)Intelligence · #6New
MAI-Image-2.5-ProImage · #7New
qwen3.8-flash-nextCoding · #8New
glm-5.3-flashCoding · #11New
| Rank | Change | Model | Score | 95% interval |
|---|---|---|---|---|
| 1 | — | Qwen-Audio-3.0-TTS-PlusClosedAlibaba | 1,240 | ±14 |
| 2 | — | StepAudio 2.5 TTSClosedStepFun | 1,206 | ±14 |
| 3 | — | Speech 2.8 HDClosedMiniMax | 1,174 | ±11 |
| 4 | — | Speech 2.8 TurboClosedMiniMax | 1,154 | ±11 |
| 5 | — | Step TTS 2 (Mar 2026)ClosedStepFun | 1,141 | ±13 |
| 6 | — | Speech 2.6 HDClosedMiniMax | 1,136 | ±11 |
| 7 | — | Speech 2.6 TurboClosedMiniMax | 1,127 | ±11 |
| 8 | — | Speech-02-HDClosedMiniMax | 1,111 | ±11 |
| 9 | — | Step Audio EditX (Mar 2026)OpenStepFun | 1,107 | ±13 |
| 10 | — | Speech-02-TurboClosedMiniMax | 1,085 | ±11 |
| 11 | — | T2A-01-HDClosedMiniMax | 1,065 | ±11 |
| 12 | — | MiMo-V2.5-TTSClosedXiaomi | 1,061 | ±13 |
| 13 | — | T2A-01-TurboClosedMiniMax | 1,032 | ±11 |
| 14 | — | MiMo-V2-TTSClosedXiaomi | 1,019 | ±13 |
| 15 | — | Qwen3 TTS FlashClosedAlibaba | 940 | ±14 |
| 16 | — | Qwen3 TTSClosedAlibaba | 925 | ±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