Skip to content
Trending storyWatching

Claude Opus 5.5 tops Arena Text leaderboard

2 reports1 sourceupdated 3 days ago

What happened

From the coverage

Anthropic 的 Claude Opus 5.5(Max 版)在 Arena 的 Code Arena WebDev 排行榜上拿了 1818 分,排第一。比第二名的 GPT-6 Astra(Max 版)高了 26 分,比自家上一代 Opus 5(Max 版)的 1692 分多了 126 分。帖子只给了分数和排名,没讲具体怎么测的、测了哪些题,所以...

From AI HOT 精选

Coverage

Follow the reports to see the story from different sides.

Sep 27
  1. AI HOT (Curated Pool)Pick
    Claude Opus 5.5 (High) tops Arena Text Arena leaderboard at 1509

    Anthropic's Claude Opus 5.5 (High) hit #1 on Arena Text Arena at 1509, 18 points ahead of Opus 5 (High). Opus 4.6 (High) sits at #2, four points behind; Anthropic takes the top six spots. The model's blended price is ~$16 per million tokens, landing it on the Pareto frontier. The post doesn't spell out evaluation dimensions or comparison model details.

Sep 24
  1. AI HOT (Curated Pool)Pick
    Claude Opus 5.5 tops Code Arena WebDev with 1818 points

    Anthropic's Claude Opus 5.5 (Max) scored 1818 on Arena's Code Arena WebDev leaderboard, taking first place. It leads GPT-6 Astra (Max) by 26 points and beats Opus 5 (Max)'s 1692 by 126 points. The post doesn't include evaluation details beyond the scores and rankings.

Heat over time

Not enough continuous observations to draw a trend yet.