GLM-5.1 Beat GPT-5.4 on SWE-Bench Pro — Did China Just Win the Coding War?

Claude Caught Exploiting SWE-Bench? The Real AI Rankings Revealed

The SWE-bench Lie: Why "95%" Says Nothing About Your Code

AI Agents Just Crossed a Dangerous Line (SWE-bench 70%+)

The Claude 5 Leak Everyone Got Wrong (1M Context, 82% SWE-Bench?)

This FREE AI Coding Agent Just Hit 70.6% on SWE-Bench (Runs Locally, Apache 2.0)

Every 'AI Beats Human Coders' Headline Just Got an Asterisk — Here's Why

Claude Opus 4.7 is HERE — SWE-bench 87.6%, /ultrareview, 3× Vision

Zhipu's 754B open model just beat GPT-5.4 on SWE-Bench Pro

Claude Opus 4 5 JUST BROKE AI RECORDS First Model to Hit 80% on SWE bench

How to Run GLM 5.2 744B Model Locally on Laptop

SWE-Explore: Benchmark for Coding Agent Exploration

We Gave a Cheaper AI Model a Map of the Code and It Matched Claude Opus