Model rankings
1203 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
StepAudio 2.5 TTSSpeech · #3New
Bach-1.0 PreviewVideo · #7New
SIMBA 3.0Speech · #7New
qwen3.6-max-previewCoding · #9New
Peanut (Open Weights Coming Soon)Image · #9New
| Rank | Change | Model | Score | 95% interval |
|---|---|---|---|---|
| 1 | — | Realtime TTS 1.5 MaxClosedInworld | 1,208 | ±18 |
| 2 | — | Gemini 3.1 Flash TTSClosedGoogle | 1,206 | ±17 |
| 3 | New | StepAudio 2.5 TTSClosedStepFun | 1,187 | ±26 |
| 4 | ▼ 1 | Eleven v3ClosedElevenLabs | 1,178 | ±12 |
| 5 | ▼ 1 | Inworld TTS 1 MaxClosedInworld | 1,164 | ±17 |
| 6 | ▼ 1 | Speech 2.8 HDClosedMiniMax | 1,163 | ±12 |
| 7 | New | SIMBA 3.0ClosedSpeechify | 1,159 | ±36 |
| 8 | ▼ 2 | Realtime TTS 1.5 MiniClosedInworld | 1,158 | ±15 |
| 9 | ▼ 2 | Step TTS 2 (Mar 2026)ClosedStepFun | 1,148 | ±19 |
| 10 | ▼ 2 | Speech 2.8 TurboClosedMiniMax | 1,146 | ±11 |
| 11 | ▼ 2 | Speech 2.6 HDClosedMiniMax | 1,133 | ±12 |
| 12 | ▼ 2 | Speech 2.6 TurboClosedMiniMax | 1,129 | ±11 |
| 13 | ▼ 2 | Fish Audio S2 ProOpenFish Audio | 1,128 | ±21 |
| 14 | ▼ 2 | Azure HD 2.5ClosedMicrosoft | 1,120 | ±21 |
| 15 | ▼ 2 | Speech-02-HDClosedMiniMax | 1,117 | ±11 |
| 16 | ▼ 2 | Inworld TTS 1ClosedInworld | 1,116 | ±16 |
| 17 | ▼ 2 | Multilingual v2ClosedElevenLabs | 1,107 | ±8 |
| 18 | ▼ 2 | Step Audio EditX (Mar 2026)OpenStepFun | 1,104 | ±21 |
| 19 | ▼ 2 | TTS-1ClosedOpenAI | 1,101 | ±8 |
| 20 | ▼ 1 | Turbo v2.5ClosedElevenLabs | 1,098 | ±8 |
| 21 | ▼ 1 | TTS-1 HDClosedOpenAI | 1,097 | ±12 |
| 22 | ▼ 4 | Speech-02-TurboClosedMiniMax | 1,096 | ±11 |
| 23 | New | MiMo-V2.5-TTSClosedXiaomi | 1,089 | ±36 |
| 24 | ▼ 3 | Flash v2.5ClosedElevenLabs | 1,087 | ±9 |
| 25 | ▼ 2 | Gemini 2.5 Flash Lite TTSClosedGoogle | 1,080 | ±14 |
| 26 | ▼ 2 | Sonic 3ClosedCartesia | 1,069 | ±13 |
| 27 | ▼ 5 | Gradium TTSClosedGradium | 1,066 | ±33 |
| 28 | ▼ 2 | Magpie-Multilingual 357M (Feb 2026)OpenNVIDIA | 1,063 | ±21 |
| 29 | ▼ 4 | OpenAudio S1ClosedFish Audio | 1,063 | ±10 |
| 30 | ▼ 2 | StudioClosedGoogle | 1,062 | ±10 |
| 31 | ▼ 4 | SIMBA 1.6ClosedSpeechify | 1,060 | ±19 |
| 32 | ▼ 3 | T2A-01-HDClosedMiniMax | 1,057 | ±10 |
| 33 | ▼ 2 | Polly GenerativeClosedAmazon | 1,056 | ±11 |
| 34 | ▼ 4 | Kokoro 82M v1.0OpenKokoro | 1,056 | ±9 |
| 35 | ▼ 3 | Voxtral TTSOpenMistral | 1,056 | ±21 |
| 36 | ▼ 3 | AsyncFlow V2, asyncClosedAsync | 1,052 | ±11 |
| 37 | ▼ 3 | Maya1OpenMaya Research | 1,050 | ±13 |
| 38 | ▼ 3 | Azure NeuralClosedMicrosoft | 1,048 | ±8 |
| 39 | ▼ 3 | Sonic English (Oct 2024)ClosedCartesia | 1,047 | ±12 |
| 40 | — | Polly Long-FormClosedAmazon | 1,044 | ±19 |
| 41 | ▼ 4 | Octave 2ClosedHume AI | 1,042 | ±13 |
| 42 | ▼ 4 | Chirp 3: HDClosedGoogle | 1,040 | ±12 |
| 43 | ▼ 2 | Chatterbox HDClosedResemble AI | 1,035 | ±10 |
| 44 | ▼ 2 | JourneyClosedGoogle | 1,033 | ±18 |
| 45 | ▼ 6 | Lightning v3.1ClosedSmallest.ai | 1,033 | ±20 |
| 46 | ▼ 3 | Gemini 2.5 Flash TTS (Dec 2025)ClosedGoogle | 1,029 | ±15 |
| 47 | ▼ 3 | SIMBA 1.0ClosedSpeechify | 1,026 | ±10 |
| 48 | ▼ 1 | MAI-Voice-1ClosedMicrosoft | 1,023 | ±20 |
| 49 | ▼ 4 | Gemini 2.5 Pro (Dec 2025)ClosedGoogle | 1,023 | ±16 |
| 50 | ▼ 2 | Octave TTSClosedHume AI | 1,018 | ±10 |
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