# 开源模型创ARC-AGI-2最强成绩

- 来源：François Chollet (@fchollet)
- 发布时间：2026-06-25 03:01
- AIHOT 分数：64
- AIHOT 链接：https://aihot.virxact.com/items/cmqsgna0f02z1slfu8dawwhga
- 原文链接：https://x.com/fchollet/status/2069858556552298519

## AI 摘要

这是迄今为止开源模型在ARC-AGI-2上取得的最强表现。

## 正文

This is the strongest ARC-AGI-2 performance to date by an open-source model.

### 引用推文

> ARC Prize：GLM-5.2 from @Zai_org on ARC-AGI (Verified) - ARC-AGI-2: 22.8%, $0.25 - ARC-AGI-1: 77.0%, $0.19 Performance is comparable with GPT-5.4 & 5.5 (Low Reasoning Effo...