Model rankings
1512 models · 5 boards · 2 sources
Best voice
Best open model
Best from China
Top three by Score
Sonic 3.6Cartesia1,273
Gemini 3.8 Flash TTSGoogle1,260
Qwen-Audio-3.0-TTS-PlusAlibaba1,259
Top three open models
Breeze TTS 2BreezeBlue · #9 overall1,204
Fish Audio S2 ProFish Audio · #27 overall1,120
Step Audio EditX (Mar 2026)StepFun · #36 overall1,094
This week's changes
claude-opus-5.5-maxCoding · #1New
Gemini 3.8 Flash TTSSpeech · #2New
Grok Imagine Image 2.0Image · #4New
gpt-6-sol-maxCoding · #5New
Gemini 3.8 Flash-Lite TTSSpeech · #6New
| Rank | Change | Model | Score | 95% interval |
|---|---|---|---|---|
| 1 | — | Breeze TTS 2OpenBreezeBlue | 1,204 | ±16 |
| 2 | — | Fish Audio S2 ProOpenFish Audio | 1,120 | ±13 |
| 3 | — | Step Audio EditX (Mar 2026)OpenStepFun | 1,094 | ±13 |
| 4 | — | Voxtral TTSOpenMistral | 1,076 | ±13 |
| 5 | — | Magpie-Multilingual 357M (Feb 2026)OpenNVIDIA | 1,063 | ±13 |
| 6 | — | Kokoro 82M v1.0OpenKokoro | 1,061 | ±11 |
| 7 | New | OpenAudio S1 MiniOpenFish Audio | 1,041 | ±20 |
| 8 | ▼ 1 | Maya1OpenMaya Research | 1,041 | ±12 |
| 9 | ▼ 1 | Higgs Audio V3 TTSOpenBoson AI | 1,033 | ±13 |
| 10 | ▼ 1 | ChatterboxOpenResemble AI | 1,021 | ±11 |
| 11 | ▼ 1 | Zonos-v0.1OpenZyphra | 1,000 | ±0 |
| 12 | New | VibeVoice 1.5BOpenMicrosoft | 951 | ±14 |
| 13 | ▼ 1 | OpenVoice v2OpenOpenVoice | 946 | ±13 |
| 14 | ▼ 1 | XTTS v2OpenCoqui | 914 | ±15 |
| 15 | ▼ 1 | StyleTTS 2OpenStyleTTS | 891 | ±15 |
| 16 | ▼ 1 | MetaVoice v1OpenMetaVoice | 845 | ±18 |
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