Model rankings
1190 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 TTSGoogle1,203
Eleven v3ElevenLabs1,177
Top three open models
Fish Audio S2 ProFish Audio · #11 overall1,124
Step Audio EditX (Mar 2026)StepFun · #16 overall1,101
Magpie-Multilingual 357M (Feb 2026)NVIDIA · #26 overall1,063
This week's changes
gpt-5.5-high (codex-harness)Coding · #7New
Grok 4.3Intelligence · #8New
mimo-v2.5-proCoding · #9New
DeepSeek V4 Pro (Reasoning, Max Effort)Intelligence · #13New
gpt-5.5 (codex-harness)Coding · #15New
| Rank | Change | Model | Score | 95% interval |
|---|---|---|---|---|
| 1 | — | Speech 2.8 HDClosedMiniMax | 1,164 | ±12 |
| 2 | — | Step TTS 2 (Mar 2026)ClosedStepFun | 1,149 | ±20 |
| 3 | — | Speech 2.8 TurboClosedMiniMax | 1,146 | ±12 |
| 4 | — | Speech 2.6 HDClosedMiniMax | 1,133 | ±12 |
| 5 | — | Speech 2.6 TurboClosedMiniMax | 1,128 | ±11 |
| 6 | — | Speech-02-HDClosedMiniMax | 1,117 | ±11 |
| 7 | — | Step Audio EditX (Mar 2026)OpenStepFun | 1,101 | ±22 |
| 8 | — | Speech-02-TurboClosedMiniMax | 1,098 | ±12 |
| 9 | — | T2A-01-HDClosedMiniMax | 1,057 | ±10 |
| 10 | ▲ 1 | T2A-01-TurboClosedMiniMax | 1,018 | ±10 |
| 11 | ▼ 1 | MiMo-V2-TTSClosedXiaomi | 1,013 | ±20 |
| 12 | — | Qwen3 TTSClosedAlibaba | 932 | ±16 |
| 13 | — | 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