模型排行
1190 个模型 · 5 个榜单 · 2 个数据来源
语音王座
开源之光
国产之光
开源前三甲
Fish Audio S2 ProFish Audio · 总第 11 名1,124
Step Audio EditX (Mar 2026)StepFun · 总第 16 名1,101
Magpie-Multilingual 357M (Feb 2026)NVIDIA · 总第 26 名1,063
这一期的变化
gpt-5.5-high (codex-harness)编程榜 · 第 7新上榜
Grok 4.3智力榜 · 第 8新上榜
mimo-v2.5-pro编程榜 · 第 9新上榜
DeepSeek V4 Pro (Reasoning, Max Effort)智力榜 · 第 13新上榜
gpt-5.5 (codex-harness)编程榜 · 第 15新上榜
| 排名 | 变化 | 模型 | 得分 | 置信区间 |
|---|---|---|---|---|
| 1 | — | Realtime TTS 1.5 Max闭源Inworld | 1,208 | ±18 |
| 2 | — | Gemini 3.1 Flash TTS闭源Google | 1,203 | ±18 |
| 3 | — | Eleven v3闭源ElevenLabs | 1,177 | ±12 |
| 4 | — | Inworld TTS 1 Max闭源Inworld | 1,166 | ±18 |
| 5 | — | Speech 2.8 HD闭源MiniMax | 1,164 | ±12 |
| 6 | — | Realtime TTS 1.5 Mini闭源Inworld | 1,159 | ±16 |
| 7 | — | Step TTS 2 (Mar 2026)闭源StepFun | 1,149 | ±20 |
| 8 | — | Speech 2.8 Turbo闭源MiniMax | 1,146 | ±12 |
| 9 | — | Speech 2.6 HD闭源MiniMax | 1,133 | ±12 |
| 10 | — | Speech 2.6 Turbo闭源MiniMax | 1,128 | ±11 |
| 11 | — | Fish Audio S2 Pro开源Fish Audio | 1,124 | ±21 |
| 12 | — | Azure HD 2.5闭源Microsoft | 1,122 | ±21 |
| 13 | — | Speech-02-HD闭源MiniMax | 1,117 | ±11 |
| 14 | — | Inworld TTS 1闭源Inworld | 1,114 | ±16 |
| 15 | — | Multilingual v2闭源ElevenLabs | 1,106 | ±8 |
| 16 | — | Step Audio EditX (Mar 2026)开源StepFun | 1,101 | ±22 |
| 17 | ▲ 1 | TTS-1闭源OpenAI | 1,100 | ±8 |
| 18 | ▼ 1 | Speech-02-Turbo闭源MiniMax | 1,098 | ±12 |
| 19 | — | Turbo v2.5闭源ElevenLabs | 1,097 | ±8 |
| 20 | — | TTS-1 HD闭源OpenAI | 1,097 | ±12 |
| 21 | — | Flash v2.5闭源ElevenLabs | 1,085 | ±9 |
| 22 | 新 | Gradium TTS闭源Gradium | 1,084 | ±53 |
| 23 | ▼ 1 | Gemini 2.5 Flash Lite TTS闭源Google | 1,079 | ±14 |
| 24 | — | Sonic 3闭源Cartesia | 1,068 | ±13 |
| 25 | — | OpenAudio S1闭源Fish Audio | 1,063 | ±11 |
| 26 | ▼ 3 | Magpie-Multilingual 357M (Feb 2026)开源NVIDIA · 另有 1 个档位 | 1,063 | ±21 |
| 27 | ▼ 1 | SIMBA 1.6闭源Speechify | 1,061 | ±20 |
| 28 | ▼ 1 | Studio闭源Google | 1,060 | ±10 |
| 29 | ▼ 1 | T2A-01-HD闭源MiniMax | 1,057 | ±10 |
| 30 | ▼ 1 | Kokoro 82M v1.0开源Kokoro | 1,055 | ±9 |
| 31 | ▼ 1 | Polly Generative闭源Amazon | 1,055 | ±11 |
| 32 | ▲ 1 | Voxtral TTS开源Mistral | 1,052 | ±21 |
| 33 | ▼ 2 | AsyncFlow V2, async闭源Async | 1,052 | ±11 |
| 34 | ▼ 2 | Maya1开源Maya Research | 1,050 | ±13 |
| 35 | ▼ 1 | Azure Neural闭源Microsoft | 1,047 | ±8 |
| 36 | ▼ 1 | Sonic English (Oct 2024)闭源Cartesia | 1,045 | ±12 |
| 37 | ▼ 1 | Octave 2闭源Hume AI | 1,042 | ±14 |
| 38 | — | Chirp 3: HD闭源Google | 1,040 | ±13 |
| 39 | ▲ 7 | Lightning v3.1闭源Smallest.ai | 1,039 | ±21 |
| 40 | ▼ 3 | Polly Long-Form闭源Amazon | 1,038 | ±19 |
| 41 | ▼ 2 | Chatterbox HD闭源Resemble AI | 1,034 | ±10 |
| 42 | ▼ 1 | Journey闭源Google | 1,029 | ±18 |
| 43 | ▼ 3 | Gemini 2.5 Flash TTS (Dec 2025)闭源Google | 1,028 | ±15 |
| 44 | ▼ 2 | SIMBA 1.0闭源Speechify | 1,024 | ±10 |
| 45 | ▼ 2 | Gemini 2.5 Pro (Dec 2025)闭源Google | 1,022 | ±16 |
| 46 | ▼ 1 | T2A-01-Turbo闭源MiniMax | 1,018 | ±10 |
| 47 | — | MAI-Voice-1闭源Microsoft | 1,018 | ±21 |
| 48 | — | Octave TTS闭源Hume AI | 1,017 | ±10 |
| 49 | ▼ 5 | MiMo-V2-TTS闭源Xiaomi | 1,013 | ±20 |
| 50 | ▼ 1 | Fish Speech 1.5开源Fish Audio | 1,012 | ±10 |
智力进步
涨得最多 · Anthropic +57.2目前最高 · Anthropic 64.6最高与最低相差 18.1 分时间范围 2025年11月 – 2026年11月
64.6Anthropic60.0Google56.9OpenAI50.1Meta46.5Kimi