Skip to content
IFAI

Model rankings

828 models · 5 boards · 2 sources

Text-to-speech arena · Anonymous head-to-head votes · Updated November 29, 2025

Best voice
Inworld TTS 1 MaxInworld1,193Score
Best open model
Kokoro 82M v1.0Kokoro1,055Score
Best from China
Speech-02-HDMiniMax1,131Score
Top three by Score
1Inworld TTS 1 MaxInworld1,193
2Speech-02-HDMiniMax1,131
3Speech-02-TurboMiniMax1,117
Top three open models
1Kokoro 82M v1.0Kokoro · #13 overall1,055
2Maya1Maya Research · #20 overall1,033
3Fish Speech 1.5Fish Audio · #22 overall1,030
This week's changes
Gemini 3 Pro PreviewIntelligence · #1New
claude-opus-4-5-20251101Coding · #2New
Grok 4.1 Fast (Reasoning)Intelligence · #10New
deepseek-v3.2-expCoding · #14New
RankChangeModelScore95% interval
1—TTS-1ClosedOpenAI1,114—
2▲ 2TTS-1 HDClosedOpenAI1,065—
3—Polly Long-FormClosedAmazon1,063—
4▼ 2Polly GenerativeClosedAmazon1,062—
5—Azure NeuralClosedMicrosoft Azure1,049—
6—GPT-4o mini TTSClosedOpenAI1,047—
7▲ 3StudioClosedGoogle1,037—
8▲ 3Magpie MultilingualClosedNVIDIA1,032—
9▲ 3JourneyClosedGoogle1,022—
10▼ 3Chirp 3: HDClosedGoogle1,016—
11▲ 2VibeVoice 1.5BClosedMicrosoft Azure994—
12▲ 2Polly NeuralClosedAmazon922—
13▲ 2WaveNetClosedGoogle892—
14▲ 2StandardClosedGoogle862—
15▲ 2Neural2ClosedGoogle859—
16▲ 2Polly StandardClosedAmazon827—

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 “—”.