Model rankings
1501 models · 5 boards · 2 sources
Best voice
Best open model
Best from China
Top three by Score
Sonic 3.6Cartesia1,282
Realtime TTS-2Inworld1,252
Qwen-Audio-3.0-TTS-PlusAlibaba1,241
Top three open models
Breeze TTS 2BreezeBlue · #7 overall1,215
Fish Audio S2 ProFish Audio · #25 overall1,128
Step Audio EditX (Mar 2026)StepFun · #32 overall1,104
This week's changes
GPT Image 2.5 Flare (max)Image · #1New
GPT Image 2.5 Sunburst (max)Image · #2New
DeepSeek V4.1 Flash (Reasoning, Max Effort)Intelligence · #20New
Agnes 3.0 FlashIntelligence · #27New
Ling-3.0-flash-VLIntelligence · #77New
| Rank | Change | Model | Score | 95% interval |
|---|---|---|---|---|
| 1 | — | Breeze TTS 2OpenBreezeBlue | 1,215 | ±17 |
| 2 | — | Fish Audio S2 ProOpenFish Audio | 1,128 | ±12 |
| 3 | — | Step Audio EditX (Mar 2026)OpenStepFun | 1,104 | ±13 |
| 4 | — | Voxtral TTSOpenMistral | 1,078 | ±13 |
| 5 | — | Magpie-Multilingual 357M (Feb 2026)OpenNVIDIA | 1,065 | ±13 |
| 6 | — | Kokoro 82M v1.0OpenKokoro | 1,060 | ±11 |
| 7 | — | Maya1OpenMaya Research | 1,043 | ±12 |
| 8 | — | Higgs Audio V3 TTSOpenBoson AI | 1,038 | ±13 |
| 9 | — | ChatterboxOpenResemble AI | 1,021 | ±11 |
| 10 | — | Zonos-v0.1OpenZyphra | 1,000 | ±0 |
| 11 | — | VibeVoice 7BOpenMicrosoft | 969 | ±13 |
| 12 | — | OpenVoice v2OpenOpenVoice | 955 | ±13 |
| 13 | — | XTTS v2OpenCoqui | 922 | ±14 |
| 14 | — | StyleTTS 2OpenStyleTTS | 893 | ±15 |
| 15 | — | MetaVoice v1OpenMetaVoice | 840 | ±17 |
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