Model rankings
1227 models · 5 boards · 2 sources
Best voice
Best open model
Best from China
Top three by Score
Sonic 3.5Cartesia1,218
Gemini 3.1 Flash TTSGoogle1,209
Realtime TTS 1.5 MaxInworld1,194
Top three open models
Fish Audio S2 ProFish Audio · #15 overall1,124
Step Audio EditX (Mar 2026)StepFun · #18 overall1,112
Voxtral TTSMistral · #31 overall1,070
This week's changes
Sonic 3.5Speech · #1New
Qwen3.7 MaxIntelligence · #5New
Gemini 3.5 Flash (high)Intelligence · #6New
grok-imagine-image-qualityImage · #6New
gemini-3.5-flashCoding · #7New
| Rank | Change | Model | Score | 95% interval |
|---|---|---|---|---|
| 1 | New | Sonic 3.5ClosedCartesia | 1,218 | ±16 |
| 2 | — | Gemini 3.1 Flash TTSClosedGoogle | 1,209 | ±14 |
| 3 | ▼ 2 | Realtime TTS 1.5 MaxClosedInworld | 1,194 | ±14 |
| 4 | ▼ 1 | StepAudio 2.5 TTSClosedStepFun | 1,187 | ±15 |
| 5 | ▼ 1 | Eleven v3ClosedElevenLabs | 1,184 | ±12 |
| 6 | — | Speech 2.8 HDClosedMiniMax | 1,168 | ±12 |
| 7 | ▼ 2 | Inworld TTS 1 MaxClosedInworld | 1,164 | ±13 |
| 8 | New | Realtime TTS-2 - Research PreviewClosedInworld | 1,158 | ±14 |
| 9 | ▼ 1 | Realtime TTS 1.5 MiniClosedInworld | 1,158 | ±12 |
| 10 | ▼ 1 | Step TTS 2 (Mar 2026)ClosedStepFun | 1,150 | ±14 |
| 11 | ▼ 1 | Speech 2.8 TurboClosedMiniMax | 1,145 | ±11 |
| 12 | — | Speech 2.6 TurboClosedMiniMax | 1,140 | ±11 |
| 13 | ▼ 2 | Speech 2.6 HDClosedMiniMax | 1,137 | ±11 |
| 14 | ▼ 7 | SIMBA 3.0ClosedSpeechify | 1,136 | ±13 |
| 15 | — | Inworld TTS 1ClosedInworld | 1,120 | ±12 |
| 16 | ▼ 2 | Speech-02-HDClosedMiniMax | 1,117 | ±11 |
| 17 | ▼ 4 | Azure HD 2.5ClosedMicrosoft | 1,110 | ±14 |
| 18 | ▼ 2 | Multilingual v2ClosedElevenLabs | 1,110 | ±10 |
| 19 | ▼ 1 | Turbo v2.5ClosedElevenLabs | 1,107 | ±10 |
| 20 | ▼ 1 | TTS-1 HDClosedOpenAI | 1,095 | ±11 |
| 21 | New | Seed-TTS 2.0ClosedByteDance Seed | 1,095 | ±15 |
| 22 | ▼ 5 | TTS-1ClosedOpenAI | 1,094 | ±10 |
| 23 | ▼ 1 | Flash v2.5ClosedElevenLabs | 1,092 | ±10 |
| 24 | ▼ 4 | Speech-02-TurboClosedMiniMax | 1,091 | ±11 |
| 25 | ▼ 4 | MiMo-V2.5-TTSClosedXiaomi | 1,090 | ±14 |
| 26 | ▼ 2 | Sonic 3ClosedCartesia | 1,082 | ±11 |
| 27 | — | StudioClosedGoogle | 1,077 | ±11 |
| 28 | ▼ 5 | Gemini 2.5 Flash Lite TTSClosedGoogle | 1,076 | ±12 |
| 29 | — | T2A-01-HDClosedMiniMax | 1,067 | ±11 |
| 30 | — | Polly GenerativeClosedAmazon | 1,066 | ±11 |
| 31 | ▼ 3 | SIMBA 1.6ClosedSpeechify | 1,063 | ±13 |
| 32 | — | Azure NeuralClosedMicrosoft | 1,063 | ±11 |
| 33 | ▼ 7 | OpenAudio S1ClosedFish Audio | 1,062 | ±11 |
| 34 | ▼ 9 | Gradium TTSClosedGradium | 1,061 | ±14 |
| 35 | ▼ 4 | AsyncFlow V2, asyncClosedAsync | 1,060 | ±11 |
| 36 | ▼ 2 | Polly Long-FormClosedAmazon | 1,057 | ±13 |
| 37 | ▼ 4 | Sonic English (Oct 2024)ClosedCartesia | 1,054 | ±11 |
| 38 | ▼ 3 | Octave 2ClosedHume AI | 1,052 | ±12 |
| 39 | ▼ 3 | Chirp 3: HDClosedGoogle | 1,048 | ±11 |
| 40 | ▼ 2 | JourneyClosedGoogle | 1,044 | ±13 |
| 41 | ▼ 2 | Lightning v3.1ClosedSmallest.ai | 1,040 | ±13 |
| 42 | ▼ 2 | Gemini 2.5 Flash TTS (Dec 2025)ClosedGoogle | 1,035 | ±12 |
| 43 | ▲ 1 | Octave TTSClosedHume AI | 1,032 | ±11 |
| 44 | ▼ 3 | SIMBA 1.0ClosedSpeechify | 1,032 | ±11 |
| 45 | ▼ 2 | Gemini 2.5 Pro (Dec 2025)ClosedGoogle | 1,031 | ±12 |
| 46 | ▼ 9 | Chatterbox HDClosedResemble AI | 1,029 | ±11 |
| 47 | New | CodaClosedRime | 1,028 | ±14 |
| 48 | ▼ 3 | T2A-01-TurboClosedMiniMax | 1,023 | ±10 |
| 49 | ▼ 3 | MiMo-V2-TTSClosedXiaomi | 1,019 | ±14 |
| 50 | ▼ 8 | MAI-Voice-1ClosedMicrosoft | 1,010 | ±14 |
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