Model rankings
1055 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
GPT-5.4 (xhigh)Intelligence · #2New
gpt-5.4-high (codex-harness)Coding · #5New
gpt-5.4-medium (codex-harness)Coding · #12New
Step 3.5 FlashIntelligence · #35New
Gemini 3.1 Flash-Lite PreviewIntelligence · #46New
| Rank | Change | Model | Score | 95% interval |
|---|---|---|---|---|
| 1 | — | Inworld TTS 1 MaxClosedInworld | 1,162 | — |
| 2 | — | Inworld TTS 1.5 MaxClosedInworld | 1,115 | — |
| 3 | — | TTS-1ClosedOpenAI | 1,111 | — |
| 4 | — | Speech-02-TurboClosedMiniMax | 1,107 | — |
| 5 | — | Multilingual v2ClosedElevenLabs | 1,105 | — |
| 6 | — | Speech-02-HDClosedMiniMax | 1,105 | — |
| 7 | — | Speech 2.6 HDClosedMiniMax | 1,105 | — |
| 8 | — | Speech 2.6 TurboClosedMiniMax | 1,103 | — |
| 9 | — | Turbo v2.5ClosedElevenLabs | 1,096 | — |
| 10 | — | ElevenLabs v3 - AlphaClosedElevenLabs | 1,095 | — |
| 11 | — | Inworld TTS 1ClosedInworld | 1,095 | — |
| 12 | — | Flash v2.5ClosedElevenLabs | 1,088 | — |
| 13 | — | Step TTS 2ClosedStepFun | 1,075 | — |
| 14 | — | OpenAudio S1ClosedFish Audio | 1,070 | — |
| 15 | — | OpenAudio S1 MiniClosedFish Audio | 1,061 | — |
| 16 | — | Kokoro 82M v1.0OpenKokoro | 1,060 | — |
| 17 | — | TTS-1 HDClosedOpenAI | 1,059 | — |
| 18 | — | Polly GenerativeClosedAmazon | 1,057 | — |
| 19 | — | T2A-01-HDClosedMiniMax | 1,056 | — |
| 20 | — | Sonic 3ClosedCartesia | 1,054 | — |
| 21 | — | Polly Long-FormClosedAmazon | 1,053 | — |
| 22 | — | Octave 2ClosedHume AI | 1,051 | — |
| 23 | — | Azure NeuralClosedMicrosoft Azure | 1,050 | — |
| 24 | — | Chatterbox HDClosedResemble AI | 1,048 | — |
| 25 | — | StudioClosedGoogle | 1,045 | — |
| 26 | — | GPT-4o mini TTSClosedOpenAI | 1,044 | — |
| 27 | — | Async Flash v1.0ClosedAsync | 1,041 | — |
| 28 | — | Sonic English (Oct '24)ClosedCartesia | 1,033 | — |
| 29 | — | T2A-01-TurboClosedMiniMax | 1,032 | — |
| 30 | — | SimbaClosedSpeechify | 1,032 | — |
| 31 | — | Maya1OpenMaya Research | 1,030 | — |
| 32 | — | Chirp 3: HDClosedGoogle | 1,027 | — |
| 33 | — | Octave TTSClosedHume AI | 1,027 | — |
| 34 | — | Gemini 2.5 Pro (Dec 2025)ClosedGoogle | 1,026 | — |
| 35 | — | Fish Speech 1.5OpenFish Audio | 1,026 | — |
| 36 | — | JourneyClosedGoogle | 1,025 | — |
| 37 | — | Gemini 2.5 Flash TTSClosedGoogle · 1 more variant | 1,023 | — |
| 38 | — | Gemini 2.5 Pro TTSClosedGoogle | 1,022 | — |
| 39 | — | ChatterboxOpenResemble AI | 1,013 | — |
| 40 | — | Gemini 2.5 Flash Lite TTSClosedGoogle | 1,013 | — |
| 41 | — | Magpie-Multilingual 357MOpenNVIDIA | 1,006 | — |
| 42 | — | Zonos-v0.1OpenZyphra | 1,000 | — |
| 43 | — | Magpie MultilingualClosedNVIDIA | 992 | — |
| 44 | — | Murf Speech Gen 2ClosedMurf AI | 987 | — |
| 45 | — | LMNTClosedLMNT | 982 | — |
| 46 | — | VibeVoice 1.5BClosedMicrosoft Azure | 980 | — |
| 47 | — | Qwen3 TTS FlashClosedAlibaba | 974 | — |
| 48 | — | OpenVoice v2OpenOpenVoice | 973 | — |
| 49 | — | VibeVoice 7BOpenMicrosoft Azure | 970 | — |
| 50 | — | 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