Skip to content
IFAI

Model rankings

866 models · 5 boards · 2 sources

‹
Week of November 2, 2026
November 9, 202636 changesNovember 2, 202641 changesOctober 26, 20269 changesOctober 19, 2026247 changesOctober 12, 2026127 changesOctober 5, 202634 changesSeptember 28, 202617 changesSeptember 21, 2026115 changesSeptember 14, 2026174 changesSeptember 7, 2026144 changesAugust 31, 202620 changesAugust 24, 202615 changes
›

Text-to-speech arena · Anonymous head-to-head votes · Updated November 3, 2026

Best voice
Eleven v4ElevenLabs1,334Score
Best open model
Fish Audio Drama 3Fish Audio1,272Score
Best from China
Qwen-Audio-3.1-TTS-PlusAlibaba1,301Score
Top three by Score
1Eleven v4ElevenLabs1,334
2Eleven v4 TurboElevenLabs1,331
3Qwen-Audio-3.1-TTS-PlusAlibaba1,301
Top three open models
1Fish Audio Drama 3Fish Audio · #6 overall1,272
2Fish Audio Drama 3 PreviewFish Audio · #12 overall1,239
3Breeze TTS 2BreezeBlue · #13 overall1,226
This week's changes
Gemini 4 Carbon (High)Intelligence · #1New
GPT-6.1 Terra (Max)Intelligence · #6New
Fish Audio Drama 3Speech · #6New
P-Video-2-ProVideo · #11New
AssemblyAI-TTS-1Speech · #14New
AllOpenClosed
All regionsUSChina
One row per modelAll variants
RankChangeModelScore95% interval
1—Ming-3.0-ttsOpenAnt Group1,189±13
2—Step Audio EditX (Mar 2026)OpenStepFun1,097±12

Intelligence over time

Each maker's best model at the time on the Artificial Analysis Intelligence Index, by the month it was released.

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

Arena data comes from the leaderboard dataset it publishes on Hugging Face (CC BY 4.0). Only each board's overall leaderboard is used; scores and ranks are unchanged. dataset · CC BY 4.0

Artificial Analysis data comes from its API (artificialanalysis.ai). Scores are unchanged; ranks follow the scores. artificialanalysis.ai

Open or closed follows the license Arena gives; prices and Artificial Analysis intelligence show only where model names match, otherwise “—”.