Model rankings
1260 models · 5 boards · 2 sources
Best voice
Best open model
Best from China
Top three by Score
Fun-Realtime-TTSAlibaba1,231
Gemini 3.1 Flash TTSGoogle1,229
xAI Text to SpeechxAI1,208
Top three open models
Fish Audio S2 ProFish Audio · #19 overall1,122
Step Audio EditX (Mar 2026)StepFun · #22 overall1,112
Voxtral TTSMistral · #36 overall1,080
This week's changes
Fun-Realtime-TTSSpeech · #1New
claude-opus-4-8-thinkingCoding · #2New
Cosmos3-Super-Text2Image (agentic)Image · #5New
minimax-m3Coding · #6New
Krea 2 MediumImage · #7New
| Rank | Change | Model | Score | 95% interval |
|---|---|---|---|---|
| 1 | — | Fish Audio S2 ProOpenFish Audio | 1,122 | ±14 |
| 2 | — | Step Audio EditX (Mar 2026)OpenStepFun | 1,112 | ±15 |
| 3 | — | Voxtral TTSOpenMistral | 1,080 | ±15 |
| 4 | — | Kokoro 82M v1.0OpenKokoro | 1,059 | ±11 |
| 5 | — | Magpie-Multilingual 357M (Feb 2026)OpenNVIDIA | 1,054 | ±15 |
| 6 | — | Maya1OpenMaya Research | 1,034 | ±14 |
| 7 | ▲ 1 | Fish Speech 1.5OpenFish Audio | 1,011 | ±11 |
| 8 | ▼ 1 | Magpie-Multilingual 357MOpenNVIDIA | 1,007 | ±12 |
| 9 | ▲ 1 | Zonos-v0.1OpenZyphra | 1,000 | ±0 |
| 10 | ▼ 1 | ChatterboxOpenResemble AI | 1,000 | ±11 |
| 11 | ▲ 1 | OpenVoice v2OpenOpenVoice | 963 | ±13 |
| 12 | ▼ 1 | VibeVoice 7BOpenMicrosoft | 962 | ±15 |
| 13 | — | XTTS v2OpenCoqui | 916 | ±15 |
| 14 | — | StyleTTS 2OpenStyleTTS | 883 | ±16 |
| 15 | — | MetaVoice v1OpenMetaVoice | 832 | ±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