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 | — | Gemini 3.1 Flash TTSClosedGoogle | 1,216 | ±13 |
| 2 | — | xAI Text to SpeechClosedxAI | 1,197 | ±14 |
| 3 | — | Azure HD 2.5ClosedMicrosoft | 1,120 | ±14 |
| 4 | — | TTS-1 HDClosedOpenAI | 1,097 | ±12 |
| 5 | — | TTS-1ClosedOpenAI | 1,086 | ±11 |
| 6 | — | Gemini 2.5 Flash Lite TTSClosedGoogle | 1,079 | ±12 |
| 7 | — | StudioClosedGoogle | 1,076 | ±12 |
| 8 | — | Polly GenerativeClosedAmazon | 1,072 | ±12 |
| 9 | New | GPT-Realtime-2ClosedOpenAI | 1,070 | ±15 |
| 10 | — | Polly Long-FormClosedAmazon | 1,066 | ±14 |
| 11 | — | Chirp 3: HDClosedGoogle | 1,057 | ±12 |
| 12 | — | JourneyClosedGoogle | 1,057 | ±13 |
| 13 | — | Gemini 2.5 Pro (Dec 2025)ClosedGoogle | 1,040 | ±13 |
| 14 | — | Gemini 2.5 Flash TTS (Dec 2025)ClosedGoogle | 1,036 | ±13 |
| 15 | ▼ 6 | Azure NeuralClosedMicrosoft | 1,035 | ±18 |
| 16 | ▼ 1 | MAI-Voice-1ClosedMicrosoft | 1,014 | ±14 |
| 17 | ▼ 1 | VibeVoice 1.5BClosedMicrosoft | 966 | ±14 |
| 18 | ▼ 1 | Magpie MultilingualClosedNVIDIA | 940 | ±14 |
| 19 | ▼ 1 | WaveNetClosedGoogle | 900 | ±12 |
| 20 | ▼ 1 | Polly NeuralClosedAmazon | 886 | ±14 |
| 21 | — | Neural2ClosedGoogle | 884 | ±12 |
| 22 | ▼ 2 | StandardClosedGoogle | 878 | ±12 |
| 23 | ▼ 1 | Polly StandardClosedAmazon | 818 | ±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