Model rankings
1160 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 TTSGoogle1,204
Eleven v3ElevenLabs1,176
Top three open models
Fish Audio S2 ProFish Audio · #11 overall1,121
Step Audio EditX (Mar 2026)StepFun · #16 overall1,101
Magpie-Multilingual 357M (Feb 2026)NVIDIA · #23 overall1,071
This week's changes
GPT-5.5 (xhigh)Intelligence · #1New
GPT Image 2 (high)Image · #1New
Realtime TTS 1.5 MaxSpeech · #1New
Claude Opus 4.7 (Adaptive Reasoning, Max Effort)Intelligence · #2New
kimi-k2.6Coding · #4New
| Rank | Change | Model | Score | 95% interval |
|---|---|---|---|---|
| 1 | New | Realtime TTS 1.5 MaxClosedInworld | 1,208 | ±19 |
| 2 | — | Gemini 3.1 Flash TTSClosedGoogle | 1,204 | ±18 |
| 3 | — | Eleven v3ClosedElevenLabs | 1,176 | ±12 |
| 4 | — | Inworld TTS 1 MaxClosedInworld | 1,165 | ±19 |
| 5 | — | Speech 2.8 HDClosedMiniMax | 1,164 | ±12 |
| 6 | New | Realtime TTS 1.5 MiniClosedInworld | 1,160 | ±16 |
| 7 | ▲ 2 | Step TTS 2 (Mar 2026)ClosedStepFun | 1,150 | ±20 |
| 8 | — | Speech 2.8 TurboClosedMiniMax | 1,146 | ±12 |
| 9 | ▲ 1 | Speech 2.6 HDClosedMiniMax | 1,132 | ±12 |
| 10 | ▲ 1 | Speech 2.6 TurboClosedMiniMax | 1,129 | ±11 |
| 11 | ▼ 5 | Fish Audio S2 ProOpenFish Audio | 1,121 | ±22 |
| 12 | ▲ 2 | Azure HD 2.5ClosedMicrosoft | 1,119 | ±22 |
| 13 | — | Speech-02-HDClosedMiniMax | 1,118 | ±11 |
| 14 | ▼ 2 | Inworld TTS 1ClosedInworld | 1,118 | ±17 |
| 15 | — | Multilingual v2ClosedElevenLabs | 1,107 | ±8 |
| 16 | — | Step Audio EditX (Mar 2026)OpenStepFun | 1,101 | ±22 |
| 17 | — | Speech-02-TurboClosedMiniMax | 1,101 | ±12 |
| 18 | — | TTS-1ClosedOpenAI | 1,101 | ±8 |
| 19 | ▲ 1 | Turbo v2.5ClosedElevenLabs | 1,097 | ±8 |
| 20 | ▼ 1 | TTS-1 HDClosedOpenAI | 1,096 | ±12 |
| 21 | — | Flash v2.5ClosedElevenLabs | 1,087 | ±9 |
| 22 | — | Gemini 2.5 Flash Lite TTSClosedGoogle | 1,077 | ±14 |
| 23 | ▲ 6 | Magpie-Multilingual 357M (Feb 2026)OpenNVIDIA · 1 more variant | 1,071 | ±24 |
| 24 | ▼ 1 | Sonic 3ClosedCartesia | 1,068 | ±13 |
| 25 | ▼ 1 | OpenAudio S1ClosedFish Audio | 1,064 | ±11 |
| 26 | ▼ 1 | SIMBA 1.6ClosedSpeechify | 1,062 | ±21 |
| 27 | ▼ 1 | StudioClosedGoogle | 1,061 | ±10 |
| 28 | ▼ 1 | T2A-01-HDClosedMiniMax | 1,059 | ±10 |
| 29 | ▼ 1 | Kokoro 82M v1.0OpenKokoro | 1,056 | ±9 |
| 30 | ▲ 1 | Polly GenerativeClosedAmazon | 1,054 | ±11 |
| 31 | ▲ 1 | AsyncFlow V2, asyncClosedAsync | 1,053 | ±12 |
| 32 | ▲ 2 | Maya1OpenMaya Research | 1,050 | ±13 |
| 33 | ▼ 3 | Voxtral TTSOpenMistral | 1,049 | ±23 |
| 34 | ▼ 1 | Azure NeuralClosedMicrosoft | 1,048 | ±8 |
| 35 | ▲ 2 | Sonic English (Oct 2024)ClosedCartesia | 1,045 | ±12 |
| 36 | ▼ 1 | Octave 2ClosedHume AI | 1,043 | ±14 |
| 37 | ▲ 1 | Polly Long-FormClosedAmazon | 1,042 | ±20 |
| 38 | ▼ 2 | Chirp 3: HDClosedGoogle | 1,041 | ±13 |
| 39 | ▲ 1 | Chatterbox HDClosedResemble AI | 1,035 | ±10 |
| 40 | ▼ 1 | Gemini 2.5 Flash TTS (Dec 2025)ClosedGoogle | 1,032 | ±15 |
| 41 | — | JourneyClosedGoogle | 1,028 | ±18 |
| 42 | — | SIMBA 1.0ClosedSpeechify | 1,026 | ±10 |
| 43 | ▲ 1 | Gemini 2.5 Pro (Dec 2025)ClosedGoogle | 1,024 | ±16 |
| 44 | ▼ 1 | MiMo-V2-TTSClosedXiaomi | 1,023 | ±22 |
| 45 | — | T2A-01-TurboClosedMiniMax | 1,021 | ±10 |
| 46 | — | Lightning v3.1ClosedSmallest.ai | 1,021 | ±23 |
| 47 | ▲ 2 | MAI-Voice-1ClosedMicrosoft | 1,021 | ±22 |
| 48 | ▼ 1 | Octave TTSClosedHume AI | 1,018 | ±10 |
| 49 | ▼ 1 | Fish Speech 1.5OpenFish Audio | 1,013 | ±10 |
| 50 | — | ChatterboxOpenResemble AI | 1,006 | ±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