모델 순위
모델 1160개 · 순위표 5개 · 데이터 출처 2곳
음성 1위
오픈 모델 1위
중국 모델 1위
오픈 모델 상위 3
Fish Audio S2 ProFish Audio · 전체 11위1,121
Step Audio EditX (Mar 2026)StepFun · 전체 16위1,101
Magpie-Multilingual 357M (Feb 2026)NVIDIA · 전체 23위1,071
이번 주 변동
GPT-5.5 (xhigh)지능 · 1위신규
GPT Image 2 (high)이미지 · 1위신규
Realtime TTS 1.5 Max음성 · 1위신규
kimi-k2.6코딩 · 4위신규
| 순위 | 변동 | 모델 | 점수 | 95% 구간 |
|---|---|---|---|---|
| 1 | 신규 | Realtime TTS 1.5 Max클로즈드Inworld | 1,208 | ±19 |
| 2 | — | Gemini 3.1 Flash TTS클로즈드Google | 1,204 | ±18 |
| 3 | — | Eleven v3클로즈드ElevenLabs | 1,176 | ±12 |
| 4 | — | Inworld TTS 1 Max클로즈드Inworld | 1,165 | ±19 |
| 5 | — | Speech 2.8 HD클로즈드MiniMax | 1,164 | ±12 |
| 6 | 신규 | Realtime TTS 1.5 Mini클로즈드Inworld | 1,160 | ±16 |
| 7 | ▲ 2 | Step TTS 2 (Mar 2026)클로즈드StepFun | 1,150 | ±20 |
| 8 | — | Speech 2.8 Turbo클로즈드MiniMax | 1,146 | ±12 |
| 9 | ▲ 1 | Speech 2.6 HD클로즈드MiniMax | 1,132 | ±12 |
| 10 | ▲ 1 | Speech 2.6 Turbo클로즈드MiniMax | 1,129 | ±11 |
| 11 | ▼ 5 | Fish Audio S2 Pro오픈Fish Audio | 1,121 | ±22 |
| 12 | ▲ 2 | Azure HD 2.5클로즈드Microsoft | 1,119 | ±22 |
| 13 | — | Speech-02-HD클로즈드MiniMax | 1,118 | ±11 |
| 14 | ▼ 2 | Inworld TTS 1클로즈드Inworld | 1,118 | ±17 |
| 15 | — | Multilingual v2클로즈드ElevenLabs | 1,107 | ±8 |
| 16 | — | Step Audio EditX (Mar 2026)오픈StepFun | 1,101 | ±22 |
| 17 | — | Speech-02-Turbo클로즈드MiniMax | 1,101 | ±12 |
| 18 | — | TTS-1클로즈드OpenAI | 1,101 | ±8 |
| 19 | ▲ 1 | Turbo v2.5클로즈드ElevenLabs | 1,097 | ±8 |
| 20 | ▼ 1 | TTS-1 HD클로즈드OpenAI | 1,096 | ±12 |
| 21 | — | Flash v2.5클로즈드ElevenLabs | 1,087 | ±9 |
| 22 | — | Gemini 2.5 Flash Lite TTS클로즈드Google | 1,077 | ±14 |
| 23 | ▲ 6 | Magpie-Multilingual 357M (Feb 2026)오픈NVIDIA · 변형 1개 더 | 1,071 | ±24 |
| 24 | ▼ 1 | Sonic 3클로즈드Cartesia | 1,068 | ±13 |
| 25 | ▼ 1 | OpenAudio S1클로즈드Fish Audio | 1,064 | ±11 |
| 26 | ▼ 1 | SIMBA 1.6클로즈드Speechify | 1,062 | ±21 |
| 27 | ▼ 1 | Studio클로즈드Google | 1,061 | ±10 |
| 28 | ▼ 1 | T2A-01-HD클로즈드MiniMax | 1,059 | ±10 |
| 29 | ▼ 1 | Kokoro 82M v1.0오픈Kokoro | 1,056 | ±9 |
| 30 | ▲ 1 | Polly Generative클로즈드Amazon | 1,054 | ±11 |
| 31 | ▲ 1 | AsyncFlow V2, async클로즈드Async | 1,053 | ±12 |
| 32 | ▲ 2 | Maya1오픈Maya Research | 1,050 | ±13 |
| 33 | ▼ 3 | Voxtral TTS오픈Mistral | 1,049 | ±23 |
| 34 | ▼ 1 | Azure Neural클로즈드Microsoft | 1,048 | ±8 |
| 35 | ▲ 2 | Sonic English (Oct 2024)클로즈드Cartesia | 1,045 | ±12 |
| 36 | ▼ 1 | Octave 2클로즈드Hume AI | 1,043 | ±14 |
| 37 | ▲ 1 | Polly Long-Form클로즈드Amazon | 1,042 | ±20 |
| 38 | ▼ 2 | Chirp 3: HD클로즈드Google | 1,041 | ±13 |
| 39 | ▲ 1 | Chatterbox HD클로즈드Resemble AI | 1,035 | ±10 |
| 40 | ▼ 1 | Gemini 2.5 Flash TTS (Dec 2025)클로즈드Google | 1,032 | ±15 |
| 41 | — | Journey클로즈드Google | 1,028 | ±18 |
| 42 | — | SIMBA 1.0클로즈드Speechify | 1,026 | ±10 |
| 43 | ▲ 1 | Gemini 2.5 Pro (Dec 2025)클로즈드Google | 1,024 | ±16 |
| 44 | ▼ 1 | MiMo-V2-TTS클로즈드Xiaomi | 1,023 | ±22 |
| 45 | — | T2A-01-Turbo클로즈드MiniMax | 1,021 | ±10 |
| 46 | — | Lightning v3.1클로즈드Smallest.ai | 1,021 | ±23 |
| 47 | ▲ 2 | MAI-Voice-1클로즈드Microsoft | 1,021 | ±22 |
| 48 | ▼ 1 | Octave TTS클로즈드Hume AI | 1,018 | ±10 |
| 49 | ▼ 1 | Fish Speech 1.5오픈Fish Audio | 1,013 | ±10 |
| 50 | — | Chatterbox오픈Resemble AI | 1,006 | ±10 |
지능의 발전
가장 많이 오름 · Anthropic +57.2현재 최고 · Anthropic 64.6최고와 최저의 차이 18.1점기간 2025년 11월 – 2026년 11월
64.6Anthropic60.0Google56.9OpenAI50.1Meta46.5Kimi