Model rankings
1412 models · 5 boards · 2 sources
Best voice
Best open model
Best from China
Top three open models
Fish Audio S2 ProFish Audio · #23 overall1,123
Step Audio EditX (Mar 2026)StepFun · #27 overall1,109
Voxtral TTSMistral · #42 overall1,071
This week's changes
Qwen-Audio-3.0-TTS-PlusSpeech · #2New
Qwen3.8 MaxIntelligence · #5New
grok-4.6-highCoding · #5New
Muse Spark 1.2 (xhigh)Intelligence · #7New
gemini-3.7-flash-highCoding · #8New
| Rank | Change | Model | Score | 95% interval |
|---|---|---|---|---|
| 1 | ▲ 1 | Fish Audio S2 ProOpenFish Audio | 1,123 | ±13 |
| 2 | ▼ 1 | Step Audio EditX (Mar 2026)OpenStepFun | 1,109 | ±14 |
| 3 | — | Voxtral TTSOpenMistral | 1,071 | ±13 |
| 4 | ▲ 2 | Magpie-Multilingual 357M (Feb 2026)OpenNVIDIA | 1,066 | ±13 |
| 5 | ▼ 1 | Kokoro 82M v1.0OpenKokoro | 1,057 | ±11 |
| 6 | ▼ 1 | Maya1OpenMaya Research | 1,043 | ±12 |
| 7 | New | Higgs Audio V3 TTSOpenBoson AI | 1,040 | ±14 |
| 8 | ▼ 1 | ChatterboxOpenResemble AI | 1,016 | ±12 |
| 9 | — | Magpie-Multilingual 357MOpenNVIDIA | 1,004 | ±12 |
| 10 | — | Zonos-v0.1OpenZyphra | 1,000 | ±0 |
| 11 | ▲ 1 | VibeVoice 7BOpenMicrosoft | 964 | ±14 |
| 12 | ▼ 1 | OpenVoice v2OpenOpenVoice | 951 | ±13 |
| 13 | — | XTTS v2OpenCoqui | 916 | ±15 |
| 14 | — | StyleTTS 2OpenStyleTTS | 888 | ±15 |
| 15 | — | MetaVoice v1OpenMetaVoice | 840 | ±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