Model rankings
1028 models · 5 boards · 2 sources
Best voice
Best open model
Best from China
Top three open models
Kokoro 82M v1.0Kokoro · #16 overall1,060
Maya1Maya Research · #31 overall1,030
Fish Speech 1.5Fish Audio · #35 overall1,026
This week's changes
Gemini 3.1 Pro PreviewIntelligence · #1New
Kling 3.0 ProVideo · #1New
claude-sonnet-4-6Coding · #2New
Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort)Intelligence · #3New
Veo 3.1Video · #5New
| Rank | Change | Model | Score | 95% interval |
|---|---|---|---|---|
| 1 | — | Speech-02-TurboClosedMiniMax | 1,107 | — |
| 2 | — | Speech-02-HDClosedMiniMax | 1,105 | — |
| 3 | — | Speech 2.6 HDClosedMiniMax | 1,105 | — |
| 4 | — | Speech 2.6 TurboClosedMiniMax | 1,103 | — |
| 5 | — | Step TTS 2ClosedStepFun | 1,075 | — |
| 6 | — | T2A-01-HDClosedMiniMax | 1,056 | — |
| 7 | — | T2A-01-TurboClosedMiniMax | 1,032 | — |
| 8 | — | Step Audio EditXOpenStepFun | 1,020 | — |
| 9 | — | Qwen3 TTS FlashClosedAlibaba | 974 | — |
| 10 | — | Step TTS MiniOpenStepFun | 959 | — |
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