Model rankings
1209 models · 5 boards · 2 sources
Best voice
Best open model
Best from China
Top three by Score
Realtime TTS 1.5 MaxInworld1,208
Gemini 3.1 Flash TTSGoogle1,206
StepAudio 2.5 TTSStepFun1,187
Top three open models
Fish Audio S2 ProFish Audio · #13 overall1,128
Step Audio EditX (Mar 2026)StepFun · #18 overall1,104
Magpie-Multilingual 357M (Feb 2026)NVIDIA · #28 overall1,063
This week's changes
gpt-5.5-xhigh (codex-harness)Coding · #7New
HiDream-O1-Image-Dev-2604Image · #11New
HiDream-O1-ImageImage · #31New
JT-35B-FlashIntelligence · #67New
granite-4.1-8bCoding · #68New
| Rank | Change | Model | Score | 95% interval |
|---|---|---|---|---|
| 1 | — | StepAudio 2.5 TTSClosedStepFun | 1,187 | ±26 |
| 2 | — | Speech 2.8 HDClosedMiniMax | 1,163 | ±12 |
| 3 | — | Step TTS 2 (Mar 2026)ClosedStepFun | 1,148 | ±19 |
| 4 | — | Speech 2.8 TurboClosedMiniMax | 1,146 | ±11 |
| 5 | — | Speech 2.6 HDClosedMiniMax | 1,133 | ±12 |
| 6 | — | Speech 2.6 TurboClosedMiniMax | 1,129 | ±11 |
| 7 | — | Speech-02-HDClosedMiniMax | 1,117 | ±11 |
| 8 | — | Step Audio EditX (Mar 2026)OpenStepFun | 1,104 | ±21 |
| 9 | — | Speech-02-TurboClosedMiniMax | 1,096 | ±11 |
| 10 | — | MiMo-V2.5-TTSClosedXiaomi | 1,089 | ±36 |
| 11 | — | T2A-01-HDClosedMiniMax | 1,057 | ±10 |
| 12 | — | T2A-01-TurboClosedMiniMax | 1,018 | ±9 |
| 13 | — | MiMo-V2-TTSClosedXiaomi | 1,011 | ±20 |
| 14 | — | Qwen3 TTSClosedAlibaba | 930 | ±15 |
| 15 | — | Qwen3 TTS FlashClosedAlibaba | 930 | ±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