That’s neat, but it’s important to note that agentic systems aren’t just comprised of the LLM. You have to take into account all the various tools the system has access to, as well as the agentic harness used to keep the LLM from going off the rails. And even with all this extra architecture, which AI firms have spent billions to perfect, the system is still just… fine. Not even as good as a junior SWE.