Model rankings
1396 models · 5 boards · 2 sources
Best voice
Best open model
Best from China
Top three open models
Step Audio EditX (Mar 2026)StepFun · #23 overall1,118
Fish Audio S2 ProFish Audio · #24 overall1,110
Voxtral TTSMistral · #34 overall1,077
This week's changes
muse-spark-1.2 (xHigh)Coding · #13New
gemini-3.5-flash-highCoding · #25New
Inkling SmallIntelligence · #36New
Celeris-1Intelligence · #221New
DeepSeek V4 Flash 0731 (Reasoning, Max Effort)Intelligence · #17Up 18
| Rank | Change | Model | Score | 95% interval |
|---|---|---|---|---|
| 1 | — | Step Audio EditX (Mar 2026)OpenStepFun | 1,118 | ±15 |
| 2 | — | Fish Audio S2 ProOpenFish Audio | 1,110 | ±15 |
| 3 | — | Voxtral TTSOpenMistral | 1,077 | ±15 |
| 4 | — | Kokoro 82M v1.0OpenKokoro | 1,060 | ±11 |
| 5 | — | Maya1OpenMaya Research | 1,053 | ±13 |
| 6 | — | Magpie-Multilingual 357M (Feb 2026)OpenNVIDIA · 1 more variant | 1,048 | ±15 |
| 7 | — | ChatterboxOpenResemble AI | 1,011 | ±12 |
| 8 | — | Fish Speech 1.5OpenFish Audio | 1,010 | ±12 |
| 9 | — | Zonos-v0.1OpenZyphra | 1,000 | ±0 |
| 10 | — | OpenVoice v2OpenOpenVoice | 959 | ±14 |
| 11 | — | VibeVoice 7BOpenMicrosoft | 958 | ±14 |
| 12 | — | XTTS v2OpenCoqui | 908 | ±15 |
| 13 | — | StyleTTS 2OpenStyleTTS | 882 | ±16 |
| 14 | — | MetaVoice v1OpenMetaVoice | 836 | ±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