Event ·Multi-source

AI 大模型周榜：代码榜榜首易主，claude-opus-4-7-thinking登顶

Arena平台发布最新周榜（2026年7月6-12日），代码榜榜首由claude-opus-4-7-thinking以ELO 1553分登顶，原榜首claude-fable-5降至第五。综合榜claude-fable-5继续蝉联第一，ELO 1505分，前五名均为Anthropic模型。国产模型最高为qwen3.7-max-preview，综合榜第17名（1475分），代码榜第12名（1526分）。glm-5.1、ernie-5.1等国产模型排名相对稳定。

Current read

想快速了解本周最强AI模型？Arena周榜给出硬核排名：代码能力claude-opus-4-7-thinking超了claude-fable-5，国产qwen3.7也稳在Top20。

11 sources67° AI heatLast updated 2026/7/14 01:44:58

Evidence

11 sources

Primary sourceIT之家

2026/7/14 01:44:58View source

Related source 1Greg Brockman

2026/7/13 00:00:54View source

Related source 2lmarena.ai

2026/7/15 16:37:10View source

Related source 3宝玉

2026/7/13 21:33:40View source

Related source 4@koltregaskes

2026/7/14 19:04:39View source

Related source 5arXiv: Anthropic

2026/7/12 17:21:32View source

Related source 6Simon Willison’s Weblog

2026/7/12 21:20:07View source

Related source 7Decoder

2026/7/13 07:54:34View source

Related source 8Fireworks AI

2026/7/15 22:35:30View source

Related source 9shao__meng

2026/7/12 13:03:22View source

Related source 10Claude

2026/7/12 17:02:05View source

Conflict check

Dedup data only shows that these sources discuss the same event, not that they agree. There is no structured supporting or refuting evidence yet, so no conflict is inferred automatically.

Open the story