Model rankings
1275 models · 5 boards · 2 sources
Best voice
Best open model
Best from China
Top three by Score
Fun-Realtime-TTSAlibaba1,226
Gemini 3.1 Flash TTSGoogle1,215
Realtime TTS-2 - Research PreviewInworld1,208
Top three open models
Fish Audio S2 ProFish Audio · #21 overall1,117
Step Audio EditX (Mar 2026)StepFun · #25 overall1,107
Voxtral TTSMistral · #37 overall1,077
This week's changes
Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback)Intelligence · #1New
claude-fable-5Coding · #1New
HiDream-O1-Image-1.5Image · #3New
MAI-Image-2.5-Flash (Foundry)Image · #8New
MAI-Image-2.5 (Foundry)Image · #12New
| Rank | Change | Model | Score | 95% interval |
|---|---|---|---|---|
| 1 | — | Fun-Realtime-TTSClosedAlibaba | 1,226 | ±16 |
| 2 | — | StepAudio 2.5 TTSClosedStepFun | 1,177 | ±16 |
| 3 | — | Speech 2.8 HDClosedMiniMax | 1,170 | ±12 |
| 4 | ▲ 1 | Step TTS 2 (Mar 2026)ClosedStepFun | 1,155 | ±14 |
| 5 | ▼ 1 | Speech 2.8 TurboClosedMiniMax | 1,152 | ±12 |
| 6 | — | Speech 2.6 TurboClosedMiniMax | 1,137 | ±11 |
| 7 | — | Speech 2.6 HDClosedMiniMax | 1,136 | ±12 |
| 8 | ▲ 1 | Speech-02-HDClosedMiniMax | 1,108 | ±12 |
| 9 | ▼ 1 | Step Audio EditX (Mar 2026)OpenStepFun | 1,107 | ±14 |
| 10 | — | Speech-02-TurboClosedMiniMax | 1,090 | ±12 |
| 11 | — | MiMo-V2.5-TTSClosedXiaomi | 1,078 | ±14 |
| 12 | — | T2A-01-HDClosedMiniMax | 1,064 | ±11 |
| 13 | — | T2A-01-TurboClosedMiniMax | 1,028 | ±11 |
| 14 | — | MiMo-V2-TTSClosedXiaomi | 1,012 | ±14 |
| 15 | ▲ 1 | Qwen3 TTS FlashClosedAlibaba | 930 | ±14 |
| 16 | ▼ 1 | Qwen3 TTSClosedAlibaba | 917 | ±13 |
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