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 | — | Fish Audio S2 ProOpenFish Audio | 1,126 | ±13 |
| 2 | — | Step Audio EditX (Mar 2026)OpenStepFun | 1,107 | ±13 |
| 3 | — | Voxtral TTSOpenMistral | 1,079 | ±13 |
| 4 | — | Magpie-Multilingual 357M (Feb 2026)OpenNVIDIA · 1 more variant | 1,065 | ±13 |
| 5 | — | Kokoro 82M v1.0OpenKokoro | 1,059 | ±11 |
| 6 | — | Maya1OpenMaya Research | 1,046 | ±12 |
| 7 | — | Higgs Audio V3 TTSOpenBoson AI | 1,042 | ±13 |
| 8 | — | ChatterboxOpenResemble AI | 1,020 | ±11 |
| 9 | — | Zonos-v0.1OpenZyphra | 1,000 | ±0 |
| 10 | — | VibeVoice 7BOpenMicrosoft | 966 | ±13 |
| 11 | — | OpenVoice v2OpenOpenVoice | 955 | ±13 |
| 12 | — | XTTS v2OpenCoqui | 921 | ±14 |
| 13 | — | StyleTTS 2OpenStyleTTS | 892 | ±15 |
| 14 | — | MetaVoice v1OpenMetaVoice | 845 | ±17 |
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