Model rankings
1133 models · 5 boards · 2 sources
Best voice
Best open model
Best from China
Top three by Score
Inworld TTS 1.5 MaxInworld1,215
Gemini 3.1 Flash TTSGoogle1,211
Eleven v3ElevenLabs1,179
Top three open models
Fish Audio S2 ProFish Audio · #6 overall1,165
Step Audio EditX (Mar 2026)StepFun · #16 overall1,105
Kokoro 82M v1.0Kokoro · #28 overall1,057
This week's changes
claude-opus-4-7Coding · #1New
Gemini 3.1 Flash TTSSpeech · #2New
ImagineArt 2.0Image · #11New
AsyncFlow V2, asyncSpeech · #32New
Lightning v3.1Speech · #46New
| Rank | Change | Model | Score | 95% interval |
|---|---|---|---|---|
| 1 | — | Inworld TTS 1.5 MaxClosedInworld | 1,215 | ±20 |
| 2 | New | Gemini 3.1 Flash TTSClosedGoogle | 1,211 | ±18 |
| 3 | ▼ 1 | Eleven v3ClosedElevenLabs | 1,179 | ±12 |
| 4 | ▼ 1 | Inworld TTS 1 MaxClosedInworld | 1,169 | ±20 |
| 5 | ▼ 1 | Speech 2.8 HDClosedMiniMax | 1,169 | ±12 |
| 6 | ▼ 1 | Inworld TTS 1.5 MiniClosedInworld | 1,165 | ±17 |
| 7 | ▼ 1 | Speech 2.8 TurboClosedMiniMax | 1,150 | ±12 |
| 8 | ▼ 1 | Step TTS 2 (Mar 2026)ClosedStepFun | 1,150 | ±27 |
| 9 | — | Speech 2.6 HDClosedMiniMax | 1,135 | ±12 |
| 10 | ▼ 2 | Speech 2.6 TurboClosedMiniMax | 1,135 | ±12 |
| 11 | ▼ 1 | Inworld TTS 1ClosedInworld | 1,123 | ±18 |
| 12 | ▼ 1 | Speech-02-HDClosedMiniMax | 1,121 | ±11 |
| 13 | — | Azure HD 2.5ClosedMicrosoft Azure | 1,112 | ±33 |
| 14 | ▼ 2 | Multilingual v2ClosedElevenLabs | 1,108 | ±8 |
| 15 | — | Speech-02-TurboClosedMiniMax | 1,103 | ±12 |
| 16 | ▼ 3 | TTS-1ClosedOpenAI | 1,102 | ±8 |
| 17 | ▼ 1 | TTS-1 HDClosedOpenAI | 1,100 | ±13 |
| 18 | ▼ 1 | Turbo v2.5ClosedElevenLabs | 1,099 | ±8 |
| 19 | ▼ 1 | Flash v2.5ClosedElevenLabs | 1,089 | ±9 |
| 20 | ▼ 1 | Gemini 2.5 Flash Lite TTSClosedGoogle | 1,081 | ±15 |
| 21 | — | Sonic 3ClosedCartesia | 1,070 | ±14 |
| 22 | — | OpenAudio S1ClosedFish Audio | 1,066 | ±11 |
| 23 | ▼ 3 | SIMBA 1.6ClosedSpeechify | 1,063 | ±22 |
| 24 | ▼ 1 | StudioClosedGoogle | 1,062 | ±10 |
| 25 | ▼ 1 | T2A-01-HDClosedMiniMax | 1,060 | ±10 |
| 26 | ▼ 1 | Polly GenerativeClosedAmazon | 1,055 | ±12 |
| 27 | New | AsyncFlow V2, asyncClosedAsync | 1,052 | ±12 |
| 28 | ▼ 2 | Azure NeuralClosedMicrosoft Azure | 1,049 | ±8 |
| 29 | — | Octave 2ClosedHume AI | 1,047 | ±14 |
| 30 | — | Chirp 3: HDClosedGoogle | 1,044 | ±13 |
| 31 | ▼ 3 | Sonic English (Oct 2024)ClosedCartesia | 1,044 | ±13 |
| 32 | ▼ 1 | Polly Long-FormClosedAmazon | 1,044 | ±20 |
| 33 | — | Gemini 2.5 Flash TTS (Dec 2025)ClosedGoogle | 1,037 | ±16 |
| 34 | ▼ 2 | Chatterbox HDClosedResemble AI | 1,036 | ±10 |
| 35 | ▼ 1 | JourneyClosedGoogle | 1,032 | ±18 |
| 36 | ▼ 1 | SIMBA 1.0ClosedSpeechify | 1,027 | ±10 |
| 37 | ▼ 1 | MiMo-V2-TTSClosedXiaomi | 1,026 | ±23 |
| 38 | ▼ 1 | Gemini 2.5 Pro (Dec 2025)ClosedGoogle | 1,025 | ±17 |
| 39 | ▼ 1 | T2A-01-TurboClosedMiniMax | 1,023 | ±10 |
| 40 | New | Lightning v3.1ClosedSmallest.ai | 1,023 | ±28 |
| 41 | ▼ 2 | Octave TTSClosedHume AI | 1,020 | ±10 |
| 42 | ▼ 1 | MAI-Voice-1ClosedMicrosoft Azure | 1,007 | ±34 |
| 43 | ▼ 3 | LMNTClosedLMNT | 967 | ±11 |
| 44 | ▼ 2 | VibeVoice 1.5BClosedMicrosoft Azure | 960 | ±16 |
| 45 | ▼ 2 | Murf Speech Gen 2ClosedMurf AI | 956 | ±10 |
| 46 | ▼ 2 | Magpie MultilingualClosedNVIDIA | 950 | ±20 |
| 47 | ▼ 2 | Neuphonic TTSClosedNeuphonic | 939 | ±19 |
| 48 | ▼ 1 | Qwen3 TTS FlashClosedAlibaba | 933 | ±18 |
| 49 | ▼ 3 | Qwen3 TTSClosedAlibaba | 929 | ±17 |
| 50 | ▼ 2 | WaveNetClosedGoogle | 872 | ±9 |
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