Model rankings
896 models · 5 boards · 2 sources
‹
Week of November 9, 2026
Best voice
Best from China
Top three by Score
Eleven v4ElevenLabs1,338
Eleven v4 TurboElevenLabs1,335
Qwen-Audio-3.1-TTS-PlusAlibaba1,299
Top three open models
This week's changes
Claude Fable 5.2 (Max, Default Fallback)Intelligence · #1New
GPT Image 2.6 Sunburst (max)Image · #1New
GPT Image 2.6 Flare (max)Image · #3New
Simba 3.5Speech · #5New
Bach 1.0 ProVideo · #7New
| Rank | Change | Model | Score | 95% interval |
|---|---|---|---|---|
| 1 | — | Gemini 3.8 Flash TTSGoogle | 1,283 | ±13 |
| 2 | — | Gemini 3.8 Flash-Lite TTSGoogle | 1,260 | ±13 |
| 3 | — | Gemini 3.1 Flash TTSGoogle | 1,214 | ±11 |
| 4 | — | Azure HD 2.5Microsoft | 1,144 | ±11 |
| 5 | — | TTS-1 HDOpenAI | 1,106 | ±11 |
| 6 | — | TTS-1OpenAI | 1,085 | ±10 |
| 7 | — | Gemini 2.5 Flash Lite TTSGoogle | 1,083 | ±11 |
| 8 | — | GPT-Realtime-2OpenAI | 1,073 | ±12 |
| 9 | — | StudioGoogle | 1,072 | ±11 |
| 10 | ▲ 1 | Gemini 2.5 Flash TTS (Dec 2025)Google | 1,070 | ±12 |
| 11 | ▼ 1 | JourneyGoogle | 1,069 | ±12 |
| 12 | — | Magpie-Multilingual 357M (Feb 2026)NVIDIA | 1,063 | ±12 |
| 12 | ▲ 1 | Polly GenerativeAmazon | 1,063 | ±11 |
| 14 | — | Chirp 3: HDGoogle | 1,062 | ±11 |
| 15 | — | Gemini 2.5 Pro (Dec 2025)ClosedGoogle | 1,038 | ±12 |
| 16 | — | Azure NeuralMicrosoft | 1,032 | ±20 |
| 17 | — | MAI-Voice-1Microsoft | 1,028 | ±12 |
| 18 | — | Polly Long-FormAmazon | 1,024 | ±13 |
| 19 | — | VibeVoice 1.5BMicrosoft | 954 | ±14 |
| 20 | — | WaveNetGoogle | 916 | ±12 |
| 21 | — | Polly NeuralAmazon | 892 | ±14 |
| 22 | — | Neural2Google | 891 | ±12 |
| 23 | — | StandardGoogle | 885 | ±12 |
| 24 | — | Polly StandardAmazon | 830 | ±15 |
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