Model rankings
1022 models · 5 boards · 2 sources
Best voice
Best open model
Best from China
Top three by Score
Eleven v4 TurboElevenLabs1,332
Eleven v4ElevenLabs1,329
Qwen-Audio-3.1-TTS-PlusAlibaba1,297
Top three open models
Fish Audio Drama 3 PreviewFish Audio · #9 overall1,247
Breeze TTS 2BreezeBlue · #11 overall1,222
Ming-3.0-ttsAnt Group · #18 overall1,188
This week's changes
HeyGen Video 1Video · #3New
Kimi K3.1 ProIntelligence · #4New
Gemini 4 Carbon (High)Coding · #4New
GPT-6.1 Terra (Max)Coding · #13New
MiniMax-M3.1-FlashIntelligence · #18New
| Rank | Change | Model | Score | 95% interval |
|---|---|---|---|---|
| 1 | — | Fish Audio Drama 3 PreviewOpenFish Audio | 1,247 | ±15 |
| 2 | — | Breeze TTS 2OpenBreezeBlue | 1,222 | ±14 |
| 3 | — | Ming-3.0-ttsOpenAnt Group | 1,188 | ±14 |
| 4 | — | Fish Audio S2 ProOpenFish Audio | 1,113 | ±12 |
| 5 | — | Step Audio EditX (Mar 2026)OpenStepFun | 1,099 | ±12 |
| 6 | — | Voxtral TTSOpenMistral | 1,091 | ±12 |
| 7 | — | Kokoro 82M v1.0OpenKokoro | 1,065 | ±11 |
| 8 | — | Magpie-Multilingual 357M (Feb 2026)OpenNVIDIA | 1,063 | ±12 |
| 9 | — | Maya1OpenMaya Research | 1,047 | ±12 |
| 10 | — | OpenAudio S1 MiniOpenFish Audio | 1,044 | ±20 |
| 11 | — | Higgs Audio V3 TTSOpenBoson AI | 1,044 | ±13 |
| 12 | — | ChatterboxOpenResemble AI | 1,024 | ±11 |
| 13 | — | Zonos-v0.1OpenZyphra | 1,000 | ±0 |
| 14 | — | VibeVoice 1.5BOpenMicrosoft | 956 | ±14 |
| 15 | — | OpenVoice v2OpenOpenVoice | 956 | ±13 |
| 16 | — | XTTS v2OpenCoqui | 916 | ±15 |
| 17 | — | StyleTTS 2OpenStyleTTS | 892 | ±15 |
| 18 | — | MetaVoice v1OpenMetaVoice | 847 | ±18 |
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