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 | — | Fun-Realtime-TTSClosedAlibaba | 1,224 | ±16 |
| 2 | — | Gemini 3.1 Flash TTSClosedGoogle | 1,222 | ±13 |
| 3 | — | Realtime TTS-2 - Research PreviewClosedInworld | 1,212 | ±13 |
| 4 | — | Sonic 3.5ClosedCartesia | 1,203 | ±15 |
| 5 | — | xAI Text to SpeechClosedxAI | 1,200 | ±14 |
| 6 | — | Realtime TTS 1.5 MaxClosedInworld | 1,198 | ±13 |
| 7 | — | Async Flash v1.5ClosedAsync | 1,186 | ±15 |
| 8 | — | StepAudio 2.5 TTSClosedStepFun | 1,181 | ±16 |
| 9 | — | Eleven v3ClosedElevenLabs | 1,181 | ±12 |
| 10 | — | Speech 2.8 HDClosedMiniMax | 1,174 | ±12 |
| 11 | New | Lightning V3.1 Pro TTS (Jun 2026)ClosedSmallest.ai | 1,172 | ±16 |
| 12 | — | Async Pro v1.0ClosedAsync | 1,165 | ±15 |
| 13 | — | Step TTS 2 (Mar 2026)ClosedStepFun | 1,159 | ±14 |
| 14 | — | Speech 2.8 TurboClosedMiniMax | 1,158 | ±12 |
| 15 | — | Realtime TTS 1.5 MiniClosedInworld | 1,158 | ±12 |
| 16 | — | Speech 2.6 TurboClosedMiniMax | 1,141 | ±11 |
| 17 | — | Speech 2.6 HDClosedMiniMax | 1,141 | ±12 |
| 18 | — | SIMBA 3.0ClosedSpeechify | 1,132 | ±13 |
| 19 | — | Azure HD 2.5ClosedMicrosoft | 1,130 | ±13 |
| 20 | ▲ 3 | Multilingual v2ClosedElevenLabs | 1,115 | ±10 |
| 21 | — | Turbo v2.5ClosedElevenLabs | 1,112 | ±10 |
| 22 | — | Speech-02-HDClosedMiniMax | 1,109 | ±11 |
| 23 | ▲ 1 | Gradium TTSClosedGradium · 1 more variant | 1,104 | ±14 |
| 24 | ▲ 2 | Flash v2.5ClosedElevenLabs | 1,099 | ±11 |
| 25 | — | TTS-1 HDClosedOpenAI | 1,099 | ±12 |
| 26 | ▲ 2 | Speech-02-TurboClosedMiniMax | 1,094 | ±12 |
| 27 | ▲ 2 | TTS-1ClosedOpenAI | 1,091 | ±10 |
| 28 | ▲ 3 | Sonic 3ClosedCartesia | 1,090 | ±12 |
| 29 | ▲ 1 | Chatterbox HDClosedResemble AI | 1,088 | ±13 |
| 30 | ▲ 2 | Gemini 2.5 Flash Lite TTSClosedGoogle | 1,088 | ±12 |
| 31 | ▲ 2 | StudioClosedGoogle | 1,086 | ±11 |
| 32 | ▲ 2 | MiMo-V2.5-TTSClosedXiaomi | 1,081 | ±14 |
| 33 | ▲ 2 | Polly GenerativeClosedAmazon | 1,076 | ±12 |
| 34 | ▲ 2 | Azure NeuralClosedMicrosoft | 1,071 | ±12 |
| 35 | ▲ 4 | OpenAudio S1ClosedFish Audio | 1,068 | ±11 |
| 36 | ▲ 2 | T2A-01-HDClosedMiniMax | 1,068 | ±11 |
| 37 | ▲ 4 | Octave 2ClosedHume AI | 1,067 | ±12 |
| 38 | ▼ 1 | Polly Long-FormClosedAmazon | 1,067 | ±13 |
| 39 | ▲ 1 | SIMBA 1.6ClosedSpeechify | 1,065 | ±13 |
| 40 | ▲ 2 | Async Flash v1.0ClosedAsync | 1,061 | ±11 |
| 41 | ▲ 2 | Chirp 3: HDClosedGoogle | 1,060 | ±12 |
| 42 | ▲ 2 | JourneyClosedGoogle | 1,058 | ±13 |
| 43 | ▲ 2 | Sonic English (Oct 2024)ClosedCartesia | 1,049 | ±12 |
| 44 | ▲ 2 | CodaClosedRime | 1,048 | ±13 |
| 45 | ▲ 2 | Gemini 2.5 Pro (Dec 2025)ClosedGoogle | 1,045 | ±12 |
| 46 | ▲ 2 | SIMBA 1.0ClosedSpeechify | 1,036 | ±11 |
| 47 | ▲ 2 | Gemini 2.5 Flash TTS (Dec 2025)ClosedGoogle | 1,036 | ±12 |
| 48 | ▲ 2 | Lightning v3.1ClosedSmallest.ai | 1,032 | ±13 |
| 49 | ▲ 3 | Octave TTSClosedHume AI | 1,031 | ±11 |
| 50 | ▲ 1 | T2A-01-TurboClosedMiniMax | 1,030 | ±11 |
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