Show HN: Multi-Agent-Coder Is #12 on Stanford's TBench. Beats Claude Code https://ift.tt/riGaL45

Show HN: Multi-Agent-Coder Is #12 on Stanford's TBench. Beats Claude Code This weekend I built a multi-agent coding system which, quite unexpectedly, beat Claude Code on Stanford's Terminal Bench! The architecture is straightforward, consisting of an orchestrator agent that deploys explorer & coder subagents to complete complex terminal based tasks, utilising an intelligent context sharing mechanism along the way which makes it all work. The repo has a lot of technical details, and all the code and prompts for you to play around with if you'd like! I had a lot of fun making this, I hope you have fun reading the README, using it yourself, or even extending it! As always, a huge thanks to the great team behind Terminal Bench. It is a great benchmark. Thanks for reading, Dan https://ift.tt/0ZLljp8 September 2, 2025 at 10:04PM