Hacker News 熱門(buzzing.cc 中文翻譯)·· 2 天前AI 評分30
Gemini 4 Neon 榮登《Models Engineering》指數榜首
Gemini 4 Neon 荣登《Models Engineering》指数榜首
AI 導讀
Gemini 4 Neon 在 Models Engineering Index 排名第一,得分為 68.0。該指數評估語言模型在工程任務上的實際表現。
正文
Mei—or, the Models Engineering Index—calculates language models' practical performance on engineering tasks. Mei calculates language models' engineering performance.
.
Performance versus .
Help spread the word with a GitHub star (opens in a new tab)
Rankings
| Index bar | |||||
|---|---|---|---|---|---|
| 1 | 4 Neon Google | 68.0 | 1.6× | 0.83× | |
| 2 | Fable 5.2 Anthropic | 65.3 | 6.4× | 2.1× | |
| 3 | 6.2 Astra OpenAI | 61.5 | 1.3× | 0.29× | |
| 4 | 4 Carbon Google | 61.4 | 1.5× | 0.89× | |
| 5 | Opus 5.5 Anthropic | 61.1 | 3.4× | 1.9× | |
| 6 | Sonnet 5.5 Anthropic | 57.8 | 3.1× | 3.4× | |
| 7 | 4 Hydrogen Google | 56.9 | 1.1× | 1× | |
| 8 | 6.2 Sol OpenAI | 55.9 | 0.37× | 0.31× | |
| 9 | 4-Max Alibaba | 49.0 | 8.2× | 1.2× | |
| 10 | K3.1 Pro Moonshot | 48.4 | 1.1× | 0.74× | |
| 11 | 6.1 Terra OpenAI | 47.0 | 0.87× | 1.7× | |
| 12 | Wonder Full Meta | 46.4 | 1.5× | 0.51× | |
| 13 | Wonder Meta | 45.5 | 1.3× | 0.62× | |
| 14 | V4.1 Flash DeepSeek | 43.6 | 0.12× | 1.5× | |
| 15 | Haiku 5.5 Anthropic | 42.9 | 0.41× | 1.7× | |
| 16 | Grok 4.7 xAI | 41.3 | 3.1× | 0.8× | |
| 17 | GLM 5.3 Z.ai | 40.4 | 2× | 1.5× | |
| 18 | Hy4 Tencent | 37.2 | 0.34× | 1.2× | |
| 19 | V2.6-Pro Xiaomi | 35.3 | 0.12× | 0.96× | |
| 20 | 6 Luna OpenAI | 34.9 | 0.064× | 0.65× |
Comparing and
來源:Hacker News 熱門(buzzing.cc 中文翻譯) · git-aarvin.github.io