---
id: 20260818-T0-01
title: "Qwen 3.8 27B跑分52，追平GPT-5.6 Luna"
title_en: "Qwen 3.8 27B Scores 52 on AI Index, Matching GPT-5.6 Luna"
url: https://ai.daily.yangsir.net/daily/20260818-T0-01
issue_date: 2026-08-18
publish_date: 2026-08-17T23:58:14.000Z
category: release
source_name: "Simon Willison"
source_url: https://simonwillison.net/2026/Aug/17/qwen-38-27b-scores-52/
---

# Qwen 3.8 27B跑分52，追平GPT-5.6 Luna

Qwen 3.8 27B在Artificial Analysis Intelligence Index上获得52分，与GPT-5.6 Luna（max）持平，仅比GLM-5.2（max）和DeepSeek V4 Pro 0813（max）低1分。值得注意的是，GLM-5.2拥有753B参数，DeepSeek V4 Pro为1.6B参数，而Qwen 3.8 27B仅以27B参数达到同等水平，展现了极高的参数效率。

## English Version

**Qwen 3.8 27B Scores 52 on AI Index, Matching GPT-5.6 Luna**

Qwen 3.8 27B scored 52 on the Artificial Analysis Intelligence Index, matching GPT-5.6 Luna (max) and just one point behind GLM-5.2 (max) and DeepSeek V4 Pro 0813 (max). Notably, GLM-5.2 has 753B parameters and DeepSeek V4 Pro has 1.6B parameters, while Qwen 3.8 27B achieves the same level with just 27B parameters, demonstrating exceptional parameter efficiency.

---

**来源**：[Simon Willison](https://simonwillison.net/2026/Aug/17/qwen-38-27b-scores-52/)

**详情页**：https://ai.daily.yangsir.net/daily/20260818-T0-01

---

*智语观潮 · Daily — https://ai.daily.yangsir.net/llms.txt*