Model rankings
1239 models · 5 boards · 2 sources
Best voice
Best open model
Best from China
Top three by Score
Gemini 3.1 Flash TTSGoogle1,214
Realtime TTS-2 - Research PreviewInworld1,209
Sonic 3.5Cartesia1,203
Top three open models
Fish Audio S2 ProFish Audio · #17 overall1,123
Step Audio EditX (Mar 2026)StepFun · #21 overall1,111
Voxtral TTSMistral · #35 overall1,067
This week's changes
Claude Opus 4.8 (Adaptive Reasoning, Max Effort)Intelligence · #1New
qwen3.7-max-20260517Coding · #3New
xAI Text to SpeechSpeech · #5New
Recraft V4.1 Utility ProImage · #6New
Fun-Realtime-TTS-PreviewSpeech · #6New
| Rank | Change | Model | Score | 95% interval |
|---|---|---|---|---|
| 1 | — | Fish Audio S2 ProOpenFish Audio | 1,123 | ±14 |
| 2 | — | Step Audio EditX (Mar 2026)OpenStepFun | 1,111 | ±14 |
| 3 | — | Voxtral TTSOpenMistral | 1,067 | ±14 |
| 4 | — | Kokoro 82M v1.0OpenKokoro | 1,062 | ±10 |
| 5 | — | Magpie-Multilingual 357M (Feb 2026)OpenNVIDIA · 1 more variant | 1,056 | ±14 |
| 6 | — | Maya1OpenMaya Research | 1,051 | ±12 |
| 7 | — | Fish Speech 1.5OpenFish Audio | 1,005 | ±11 |
| 8 | — | ChatterboxOpenResemble AI | 1,004 | ±11 |
| 9 | — | Zonos-v0.1OpenZyphra | 1,000 | ±0 |
| 10 | — | VibeVoice 7BOpenMicrosoft | 963 | ±13 |
| 11 | — | OpenVoice v2OpenOpenVoice | 949 | ±10 |
| 12 | — | XTTS v2OpenCoqui | 898 | ±12 |
| 13 | — | StyleTTS 2OpenStyleTTS | 876 | ±12 |
| 14 | — | MetaVoice v1OpenMetaVoice | 770 | ±15 |
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