130k-Star GitHub Marvel Sends GLM-5.1 Soaring, Burns 100 Million Tokens in 3 Days.

GLM-5.1-Turbo had only been in use for a few days.

Then I received a text message: Zhipu Coding Plan now supports the GLM-5.1 model.

I immediately switched my Claude Code to it, went crazy using it for two days, and burned through several hundred million tokens.

I found that GLM-5.1 isn’t just a simple .1 upgrade, but possibly a generational leap.

Especially in long-horizon task performance, GLM-5.1 is truly awesome.

Looking at core leaderboards like Artificial Analysis and SWE Bench, currently GLM-5.1 is number one in open source.

And GLM-5.1 + Superpowers plugin is a perfect match.

If you want to experience it, check out Zhipu Coding Plan. If you’re a new user, placing an order gets you an immediate 5% discount. But you have to grab it now, every day at 10 AM.

Link: https://www.bigmodel.cn/glm-coding?ic=UX7NF0VZ4S

<section style="-webkit-tap-highlight-color: rgba(0, 0, 0, 0);margin: 0px 8px 16px;padding: 0px;outline: 0px;max-width: 100%;box-sizing: border-box !important;overflow-wrap: break-word !important;font-style

Categories: 文章精选