Model rankings
1539 models · 5 boards · 2 sources
Best voice
Best open model
Best from China
Top three open models
Breeze TTS 2BreezeBlue · #10 overall1,216
Fish Audio S2 ProFish Audio · #32 overall1,117
Step Audio EditX (Mar 2026)StepFun · #39 overall1,095
This week's changes
Claude Opus 5.5 (Adaptive Reasoning, Max Effort, Default Fallback)Intelligence · #1New
Eleven v4Speech · #1New
Qwen-Audio-3.1-TTS-PlusSpeech · #2New
claude-sonnet-5.5-xhighCoding · #3New
gpt-6.1-sol-maxCoding · #4New
| Rank | Change | Model | Score | 95% interval |
|---|---|---|---|---|
| 1 | New | Eleven v4ClosedElevenLabs | 1,321 | ±18 |
| 2 | New | Qwen-Audio-3.1-TTS-PlusClosedAlibaba | 1,292 | ±18 |
| 3 | ▼ 2 | Sonic 3.6ClosedCartesia | 1,278 | ±16 |
| 4 | ▼ 2 | Gemini 3.8 Flash TTSClosedGoogle | 1,275 | ±16 |
| 5 | ▼ 2 | Qwen-Audio-3.0-TTS-PlusClosedAlibaba | 1,261 | ±15 |
| 6 | ▼ 2 | Realtime TTS-2ClosedInworld | 1,251 | ±16 |
| 7 | ▼ 2 | Simba 3.2ClosedSpeechifyAI | 1,242 | ±13 |
| 8 | ▼ 2 | Gemini 3.8 Flash-Lite TTSClosedGoogle | 1,242 | ±15 |
| 9 | ▼ 2 | Luna TTSClosedVUI Labs | 1,227 | ±13 |
| 10 | ▼ 2 | Realtime TTS-2 FlashClosedInworld | 1,214 | ±14 |
| 11 | ▼ 1 | StepAudio 2.5 TTS (Aug 2026)ClosedStepFun | 1,210 | ±15 |
| 12 | ▼ 3 | Gemini 3.1 Flash TTSClosedGoogle | 1,209 | ±12 |
| 13 | ▼ 2 | v3 ConversationalClosedElevenLabs | 1,203 | ±14 |
| 14 | ▼ 2 | Sonic 3.5ClosedCartesia | 1,190 | ±12 |
| 15 | ▼ 1 | Soniox TTS Real-Time v2ClosedSoniox | 1,179 | ±11 |
| 16 | — | Eleven v3ClosedElevenLabs | 1,174 | ±11 |
| 17 | ▼ 2 | Speech 2.8 HDClosedMiniMax | 1,173 | ±11 |
| 18 | ▼ 5 | Lightning V3.1 Pro (Jul 2026)ClosedSmallest.ai | 1,171 | ±14 |
| 19 | ▼ 2 | Falcon 2ClosedMurf AI | 1,155 | ±14 |
| 20 | ▼ 2 | Speech 2.8 TurboClosedMiniMax | 1,153 | ±11 |
| 21 | ▼ 2 | Gradium TTS (Aug 2026)ClosedGradium | 1,151 | ±14 |
| 22 | ▼ 2 | Fish Audio S2.1 ProClosedFish Audio | 1,141 | ±13 |
| 23 | ▲ 1 | Async Flash v1.5ClosedAsync | 1,136 | ±13 |
| 24 | ▼ 1 | SpaceXAI TTSClosedSpaceXAI | 1,136 | ±15 |
| 25 | ▼ 4 | Step TTS 2 (Mar 2026)ClosedStepFun | 1,134 | ±12 |
| 26 | ▼ 4 | Azure HD 2.5ClosedMicrosoft | 1,131 | ±12 |
| 27 | ▼ 2 | Speech 2.6 HDClosedMiniMax | 1,128 | ±11 |
| 28 | ▼ 2 | Simba 3.0ClosedSpeechifyAI | 1,125 | ±12 |
| 29 | ▼ 2 | Speech 2.6 TurboClosedMiniMax | 1,124 | ±11 |
| 30 | ▼ 2 | Async Pro v1.0ClosedAsync | 1,119 | ±13 |
| 31 | ▼ 2 | Speech-02-HDClosedMiniMax | 1,114 | ±11 |
| 32 | — | Speech 2.6ClosedHithink | 1,103 | ±13 |
| 33 | ▼ 3 | TTS-1 HDClosedOpenAI | 1,103 | ±12 |
| 34 | ▼ 3 | Chatterbox HDClosedResemble AI | 1,102 | ±13 |
| 35 | ▼ 2 | Turbo v2.5ClosedElevenLabs | 1,098 | ±11 |
| 36 | ▼ 2 | Multilingual v2ClosedElevenLabs | 1,097 | ±10 |
| 37 | ▼ 2 | TTS-1ClosedOpenAI | 1,090 | ±11 |
| 38 | ▼ 2 | Speech-02-TurboClosedMiniMax | 1,090 | ±12 |
| 39 | ▼ 2 | Gemini 2.5 Flash Lite TTSClosedGoogle | 1,083 | ±12 |
| 40 | ▼ 2 | OpenAudio S1ClosedFish Audio | 1,082 | ±11 |
| 41 | ▼ 2 | StudioClosedGoogle | 1,079 | ±11 |
| 42 | ▼ 2 | Flash v2.5ClosedElevenLabs | 1,078 | ±11 |
| 43 | ▼ 1 | GPT-Realtime-2ClosedOpenAI | 1,077 | ±13 |
| 44 | ▼ 3 | JourneyClosedGoogle | 1,074 | ±13 |
| 45 | ▼ 2 | Maya 2 FlashClosedMaya Research | 1,071 | ±14 |
| 46 | ▼ 2 | T2A-01-HDClosedMiniMax | 1,066 | ±11 |
| 47 | ▼ 2 | Polly GenerativeClosedAmazon | 1,065 | ±12 |
| 48 | ▼ 1 | CodaClosedRime | 1,062 | ±13 |
| 49 | ▼ 3 | Sonic 3ClosedCartesia | 1,060 | ±12 |
| 50 | ▼ 1 | Gemini 2.5 Flash TTS (Dec 2025)ClosedGoogle | 1,058 | ±12 |
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