Model rankings
1283 models · 5 boards · 2 sources
Best voice
Best open model
Best from China
Top three open models
Step Audio EditX (Mar 2026)StepFun · #21 overall1,113
Fish Audio S2 ProFish Audio · #23 overall1,111
Voxtral TTSMistral · #36 overall1,075
This week's changes
MAI-Image-2.5Image · #2New
MAI-Image-2.5-FlashImage · #9New
Luna TTSSpeech · #9New
Nex-N2-ProIntelligence · #20New
Grok Build 0.1 0616Intelligence · #29New
| Rank | Change | Model | Score | 95% interval |
|---|---|---|---|---|
| 1 | ▲ 3 | Sonic 3.5ClosedCartesia | 1,218 | ±14 |
| 2 | — | Gemini 3.1 Flash TTSClosedGoogle | 1,216 | ±13 |
| 3 | ▼ 2 | Fun-Realtime-TTSClosedAlibaba | 1,210 | ±14 |
| 4 | ▼ 1 | Realtime TTS-2 - Research PreviewClosedInworld | 1,202 | ±14 |
| 5 | — | xAI Text to SpeechClosedxAI | 1,197 | ±14 |
| 6 | — | Realtime TTS 1.5 MaxClosedInworld | 1,197 | ±14 |
| 7 | — | Async Flash v1.5ClosedAsync | 1,186 | ±15 |
| 8 | — | StepAudio 2.5 TTSClosedStepFun | 1,184 | ±17 |
| 9 | New | Luna TTSClosedVUI Labs | 1,181 | ±16 |
| 10 | ▼ 1 | Eleven v3ClosedElevenLabs | 1,179 | ±12 |
| 11 | ▼ 1 | Speech 2.8 HDClosedMiniMax | 1,171 | ±12 |
| 12 | ▼ 1 | Lightning V3.1 Pro TTS (Jun 2026)ClosedSmallest.ai | 1,167 | ±15 |
| 13 | ▼ 1 | Async Pro v1.0ClosedAsync | 1,157 | ±15 |
| 14 | — | Speech 2.8 TurboClosedMiniMax | 1,152 | ±12 |
| 15 | ▼ 2 | Step TTS 2 (Mar 2026)ClosedStepFun | 1,150 | ±14 |
| 16 | ▼ 1 | Realtime TTS 1.5 MiniClosedInworld | 1,150 | ±13 |
| 17 | ▼ 1 | Speech 2.6 TurboClosedMiniMax | 1,137 | ±12 |
| 18 | — | SIMBA 3.0ClosedSpeechify | 1,134 | ±14 |
| 19 | ▼ 2 | Speech 2.6 HDClosedMiniMax | 1,132 | ±12 |
| 20 | ▼ 1 | Azure HD 2.5ClosedMicrosoft | 1,120 | ±14 |
| 21 | ▼ 1 | Multilingual v2ClosedElevenLabs | 1,111 | ±10 |
| 22 | — | Speech-02-HDClosedMiniMax | 1,109 | ±12 |
| 23 | ▼ 2 | Turbo v2.5ClosedElevenLabs | 1,108 | ±11 |
| 24 | ▼ 1 | Gradium TTSClosedGradium | 1,104 | ±15 |
| 25 | — | TTS-1 HDClosedOpenAI | 1,097 | ±12 |
| 26 | ▼ 2 | Flash v2.5ClosedElevenLabs | 1,095 | ±11 |
| 27 | ▲ 13 | Gradium TTS (Jun 2026)ClosedGradium | 1,095 | ±16 |
| 28 | ▼ 2 | Speech-02-TurboClosedMiniMax | 1,089 | ±12 |
| 29 | ▲ 3 | MiMo-V2.5-TTSClosedXiaomi | 1,089 | ±14 |
| 30 | ▼ 1 | Chatterbox HDClosedResemble AI | 1,087 | ±13 |
| 31 | ▼ 4 | TTS-1ClosedOpenAI | 1,086 | ±11 |
| 32 | ▼ 4 | Sonic 3ClosedCartesia | 1,082 | ±12 |
| 33 | ▼ 3 | Gemini 2.5 Flash Lite TTSClosedGoogle | 1,079 | ±12 |
| 34 | ▼ 3 | StudioClosedGoogle | 1,076 | ±12 |
| 35 | ▼ 2 | Polly GenerativeClosedAmazon | 1,072 | ±12 |
| 36 | New | GPT-Realtime-2ClosedOpenAI | 1,070 | ±15 |
| 37 | ▲ 2 | SIMBA 1.6ClosedSpeechify | 1,068 | ±13 |
| 38 | ▼ 3 | OpenAudio S1ClosedFish Audio | 1,066 | ±11 |
| 39 | ▼ 1 | Polly Long-FormClosedAmazon | 1,066 | ±14 |
| 40 | ▼ 4 | T2A-01-HDClosedMiniMax | 1,062 | ±11 |
| 41 | ▼ 4 | Octave 2ClosedHume AI | 1,061 | ±12 |
| 42 | — | Chirp 3: HDClosedGoogle | 1,057 | ±12 |
| 43 | ▼ 2 | Async Flash v1.0ClosedAsync | 1,057 | ±12 |
| 44 | ▼ 1 | JourneyClosedGoogle | 1,057 | ±13 |
| 45 | — | CodaClosedRime | 1,045 | ±14 |
| 46 | ▼ 2 | Sonic English (Oct 2024)ClosedCartesia | 1,044 | ±12 |
| 47 | ▼ 1 | Gemini 2.5 Pro (Dec 2025)ClosedGoogle | 1,040 | ±13 |
| 48 | ▼ 1 | SIMBA 1.0ClosedSpeechify | 1,038 | ±11 |
| 49 | ▼ 1 | Gemini 2.5 Flash TTS (Dec 2025)ClosedGoogle | 1,036 | ±13 |
| 50 | ▼ 16 | Azure NeuralClosedMicrosoft | 1,035 | ±18 |
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