Model rankings
1190 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 TTSGoogle1,203
Eleven v3ElevenLabs1,177
Top three open models
Fish Audio S2 ProFish Audio · #11 overall1,124
Step Audio EditX (Mar 2026)StepFun · #16 overall1,101
Magpie-Multilingual 357M (Feb 2026)NVIDIA · #26 overall1,063
This week's changes
gpt-5.5-high (codex-harness)Coding · #7New
Grok 4.3Intelligence · #8New
mimo-v2.5-proCoding · #9New
DeepSeek V4 Pro (Reasoning, Max Effort)Intelligence · #13New
gpt-5.5 (codex-harness)Coding · #15New
| Rank | Change | Model | Score | 95% interval |
|---|---|---|---|---|
| 1 | — | Realtime TTS 1.5 MaxClosedInworld | 1,208 | ±18 |
| 2 | — | Gemini 3.1 Flash TTSClosedGoogle | 1,203 | ±18 |
| 3 | — | Eleven v3ClosedElevenLabs | 1,177 | ±12 |
| 4 | — | Inworld TTS 1 MaxClosedInworld | 1,166 | ±18 |
| 5 | — | Speech 2.8 HDClosedMiniMax | 1,164 | ±12 |
| 6 | — | Realtime TTS 1.5 MiniClosedInworld | 1,159 | ±16 |
| 7 | — | Step TTS 2 (Mar 2026)ClosedStepFun | 1,149 | ±20 |
| 8 | — | Speech 2.8 TurboClosedMiniMax | 1,146 | ±12 |
| 9 | — | Speech 2.6 HDClosedMiniMax | 1,133 | ±12 |
| 10 | — | Speech 2.6 TurboClosedMiniMax | 1,128 | ±11 |
| 11 | — | Fish Audio S2 ProOpenFish Audio | 1,124 | ±21 |
| 12 | — | Azure HD 2.5ClosedMicrosoft | 1,122 | ±21 |
| 13 | — | Speech-02-HDClosedMiniMax | 1,117 | ±11 |
| 14 | — | Inworld TTS 1ClosedInworld | 1,114 | ±16 |
| 15 | — | Multilingual v2ClosedElevenLabs | 1,106 | ±8 |
| 16 | — | Step Audio EditX (Mar 2026)OpenStepFun | 1,101 | ±22 |
| 17 | ▲ 1 | TTS-1ClosedOpenAI | 1,100 | ±8 |
| 18 | ▼ 1 | Speech-02-TurboClosedMiniMax | 1,098 | ±12 |
| 19 | — | Turbo v2.5ClosedElevenLabs | 1,097 | ±8 |
| 20 | — | TTS-1 HDClosedOpenAI | 1,097 | ±12 |
| 21 | — | Flash v2.5ClosedElevenLabs | 1,085 | ±9 |
| 22 | New | Gradium TTSClosedGradium | 1,084 | ±53 |
| 23 | ▼ 1 | Gemini 2.5 Flash Lite TTSClosedGoogle | 1,079 | ±14 |
| 24 | — | Sonic 3ClosedCartesia | 1,068 | ±13 |
| 25 | — | OpenAudio S1ClosedFish Audio | 1,063 | ±11 |
| 26 | ▼ 3 | Magpie-Multilingual 357M (Feb 2026)OpenNVIDIA · 1 more variant | 1,063 | ±21 |
| 27 | ▼ 1 | SIMBA 1.6ClosedSpeechify | 1,061 | ±20 |
| 28 | ▼ 1 | StudioClosedGoogle | 1,060 | ±10 |
| 29 | ▼ 1 | T2A-01-HDClosedMiniMax | 1,057 | ±10 |
| 30 | ▼ 1 | Kokoro 82M v1.0OpenKokoro | 1,055 | ±9 |
| 31 | ▼ 1 | Polly GenerativeClosedAmazon | 1,055 | ±11 |
| 32 | ▲ 1 | Voxtral TTSOpenMistral | 1,052 | ±21 |
| 33 | ▼ 2 | AsyncFlow V2, asyncClosedAsync | 1,052 | ±11 |
| 34 | ▼ 2 | Maya1OpenMaya Research | 1,050 | ±13 |
| 35 | ▼ 1 | Azure NeuralClosedMicrosoft | 1,047 | ±8 |
| 36 | ▼ 1 | Sonic English (Oct 2024)ClosedCartesia | 1,045 | ±12 |
| 37 | ▼ 1 | Octave 2ClosedHume AI | 1,042 | ±14 |
| 38 | — | Chirp 3: HDClosedGoogle | 1,040 | ±13 |
| 39 | ▲ 7 | Lightning v3.1ClosedSmallest.ai | 1,039 | ±21 |
| 40 | ▼ 3 | Polly Long-FormClosedAmazon | 1,038 | ±19 |
| 41 | ▼ 2 | Chatterbox HDClosedResemble AI | 1,034 | ±10 |
| 42 | ▼ 1 | JourneyClosedGoogle | 1,029 | ±18 |
| 43 | ▼ 3 | Gemini 2.5 Flash TTS (Dec 2025)ClosedGoogle | 1,028 | ±15 |
| 44 | ▼ 2 | SIMBA 1.0ClosedSpeechify | 1,024 | ±10 |
| 45 | ▼ 2 | Gemini 2.5 Pro (Dec 2025)ClosedGoogle | 1,022 | ±16 |
| 46 | ▼ 1 | T2A-01-TurboClosedMiniMax | 1,018 | ±10 |
| 47 | — | MAI-Voice-1ClosedMicrosoft | 1,018 | ±21 |
| 48 | — | Octave TTSClosedHume AI | 1,017 | ±10 |
| 49 | ▼ 5 | MiMo-V2-TTSClosedXiaomi | 1,013 | ±20 |
| 50 | ▼ 1 | Fish Speech 1.5OpenFish Audio | 1,012 | ±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