Model rankings
1492 models · 5 boards · 2 sources
Best voice
Best open model
Best from China
Top three by Score
Sonic 3.6Cartesia1,282
Realtime TTS-2Inworld1,252
Qwen-Audio-3.0-TTS-PlusAlibaba1,241
Top three open models
Breeze TTS 2BreezeBlue · #7 overall1,215
Fish Audio S2 ProFish Audio · #25 overall1,128
Step Audio EditX (Mar 2026)StepFun · #32 overall1,104
This week's changes
Claude Fable 5.1 (Adaptive Reasoning, Max Effort, Default Fallback)Intelligence · #1New
GPT-6 Astra (max)Intelligence · #2New
MAI-Image-2.6Image · #2New
Realtime TTS-2Speech · #2New
Muse Spark 1.3 (max)Intelligence · #5New
| Rank | Change | Model | Score | 95% interval |
|---|---|---|---|---|
| 1 | — | Sonic 3.6ClosedCartesia | 1,282 | ±17 |
| 2 | New | Realtime TTS-2ClosedInworld | 1,252 | ±18 |
| 3 | ▼ 1 | Qwen-Audio-3.0-TTS-PlusClosedAlibaba | 1,241 | ±14 |
| 4 | ▼ 1 | Simba 3.2ClosedSpeechifyAI | 1,240 | ±14 |
| 5 | ▼ 1 | Luna TTSClosedVUI Labs | 1,228 | ±14 |
| 6 | New | Realtime TTS-2 Flash - Research PreviewClosedInworld | 1,222 | ±15 |
| 7 | New | v3 ConversationalClosedElevenLabs | 1,210 | ±15 |
| 8 | ▼ 3 | Gemini 3.1 Flash TTSClosedGoogle | 1,208 | ±12 |
| 9 | ▼ 3 | StepAudio 2.5 TTS (Aug 2026)ClosedStepFun | 1,205 | ±17 |
| 10 | ▼ 3 | Sonic 3.5ClosedCartesia | 1,193 | ±12 |
| 11 | ▼ 2 | Lightning V3.1 Pro (Jul 2026)ClosedSmallest.ai | 1,190 | ±14 |
| 12 | New | Soniox TTS Real-Time v2ClosedSoniox | 1,179 | ±11 |
| 13 | ▼ 2 | Eleven v3ClosedElevenLabs | 1,175 | ±11 |
| 14 | ▼ 2 | Speech 2.8 HDClosedMiniMax | 1,171 | ±11 |
| 15 | ▼ 2 | Falcon 2ClosedMurf AI | 1,158 | ±15 |
| 16 | ▼ 2 | Speech 2.8 TurboClosedMiniMax | 1,152 | ±11 |
| 17 | ▲ 16 | Gradium TTS (Aug 2026)ClosedGradium | 1,149 | ±15 |
| 18 | ▼ 2 | Async Flash v1.5ClosedAsync | 1,141 | ±13 |
| 19 | ▼ 2 | Fish Audio S2.1 ProClosedFish Audio | 1,141 | ±13 |
| 20 | ▼ 2 | Step TTS 2 (Mar 2026)ClosedStepFun | 1,138 | ±12 |
| 21 | ▼ 2 | Speech 2.6 HDClosedMiniMax | 1,134 | ±11 |
| 22 | ▼ 2 | Lightning V3.1 Pro TTS (Jun 2026)ClosedSmallest.ai | 1,133 | ±13 |
| 23 | ▼ 1 | Azure HD 2.5ClosedMicrosoft | 1,131 | ±12 |
| 24 | — | Speech 2.6 TurboClosedMiniMax | 1,127 | ±11 |
| 25 | ▲ 1 | SpaceXAI TTSClosedSpaceXAI | 1,123 | ±16 |
| 26 | ▼ 1 | Simba 3.0ClosedSpeechifyAI | 1,122 | ±12 |
| 27 | ▼ 4 | Async Pro v1.0ClosedAsync | 1,121 | ±13 |
| 28 | ▼ 1 | Speech-02-HDClosedMiniMax | 1,112 | ±11 |
| 29 | ▼ 1 | TTS-1 HDClosedOpenAI | 1,106 | ±11 |
| 30 | ▼ 1 | Turbo v2.5ClosedElevenLabs | 1,100 | ±10 |
| 31 | ▼ 1 | Multilingual v2ClosedElevenLabs | 1,099 | ±10 |
| 32 | ▼ 1 | Chatterbox HDClosedResemble AI | 1,093 | ±12 |
| 33 | ▼ 1 | TTS-1ClosedOpenAI | 1,091 | ±10 |
| 34 | — | Gemini 2.5 Flash Lite TTSClosedGoogle | 1,084 | ±12 |
| 35 | ▲ 3 | Speech 2.6ClosedHithink | 1,084 | ±13 |
| 36 | ▼ 1 | Speech-02-TurboClosedMiniMax | 1,082 | ±11 |
| 37 | — | StudioClosedGoogle | 1,081 | ±11 |
| 38 | ▲ 1 | OpenAudio S1ClosedFish Audio | 1,080 | ±11 |
| 39 | ▼ 3 | Flash v2.5ClosedElevenLabs | 1,080 | ±11 |
| 40 | ▲ 4 | JourneyClosedGoogle | 1,075 | ±13 |
| 41 | ▲ 2 | Maya 2 FlashClosedMaya Research | 1,072 | ±14 |
| 42 | ▼ 1 | Sonic 3ClosedCartesia | 1,067 | ±11 |
| 43 | ▼ 3 | GPT-Realtime-2ClosedOpenAI | 1,067 | ±13 |
| 44 | ▲ 1 | T2A-01-HDClosedMiniMax | 1,066 | ±11 |
| 45 | ▲ 2 | Polly GenerativeClosedAmazon | 1,063 | ±11 |
| 46 | — | SIMBA 1.6ClosedSpeechifyAI | 1,062 | ±12 |
| 47 | ▲ 6 | Maya 2 GlobalClosedMaya Research | 1,059 | ±14 |
| 47 | ▲ 1 | MiMo-V2.5-TTSClosedXiaomi | 1,059 | ±13 |
| 49 | ▲ 1 | CodaClosedRime | 1,058 | ±12 |
| 50 | ▲ 1 | Chirp 3: HDClosedGoogle | 1,057 | ±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