Model rankings
1278 models · 5 boards · 2 sources
Best voice
Best open model
Best from China
Top three by Score
Fun-Realtime-TTSAlibaba1,224
Gemini 3.1 Flash TTSGoogle1,222
Realtime TTS-2 - Research PreviewInworld1,212
Top three open models
Fish Audio S2 ProFish Audio · #20 overall1,117
Step Audio EditX (Mar 2026)StepFun · #22 overall1,115
Voxtral TTSMistral · #34 overall1,081
This week's changes
glm-5.2 (max)Coding · #2New
GLM-5.2 (max)Intelligence · #6New
seed-2.1-pro-previewCoding · #6New
Lightning V3.1 Pro TTS (Jun 2026)Speech · #11New
kimi-k2.7-codeCoding · #17New
| Rank | Change | Model | Score | 95% interval |
|---|---|---|---|---|
| 1 | — | Gemini 3.1 Flash TTSClosedGoogle | 1,222 | ±13 |
| 2 | — | xAI Text to SpeechClosedxAI | 1,200 | ±14 |
| 3 | — | Azure HD 2.5ClosedMicrosoft | 1,130 | ±13 |
| 4 | — | TTS-1 HDClosedOpenAI | 1,099 | ±12 |
| 5 | — | TTS-1ClosedOpenAI | 1,091 | ±10 |
| 6 | — | Gemini 2.5 Flash Lite TTSClosedGoogle | 1,088 | ±12 |
| 7 | — | StudioClosedGoogle | 1,086 | ±11 |
| 8 | — | Polly GenerativeClosedAmazon | 1,076 | ±12 |
| 9 | — | Azure NeuralClosedMicrosoft | 1,071 | ±12 |
| 10 | — | Polly Long-FormClosedAmazon | 1,067 | ±13 |
| 11 | — | Chirp 3: HDClosedGoogle | 1,060 | ±12 |
| 12 | — | JourneyClosedGoogle | 1,058 | ±13 |
| 13 | — | Gemini 2.5 Pro (Dec 2025)ClosedGoogle | 1,045 | ±12 |
| 14 | — | Gemini 2.5 Flash TTS (Dec 2025)ClosedGoogle | 1,036 | ±12 |
| 15 | — | MAI-Voice-1ClosedMicrosoft | 1,006 | ±13 |
| 16 | — | VibeVoice 1.5BClosedMicrosoft | 965 | ±13 |
| 17 | — | Magpie MultilingualClosedNVIDIA | 943 | ±14 |
| 18 | — | WaveNetClosedGoogle | 900 | ±11 |
| 19 | — | Polly NeuralClosedAmazon | 889 | ±14 |
| 20 | — | StandardClosedGoogle | 880 | ±12 |
| 21 | — | Neural2ClosedGoogle | 878 | ±12 |
| 22 | — | Polly StandardClosedAmazon | 814 | ±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