alt Hacker NewsThe harness matters far more than most people think. This post about the CORE benchmark where Opus’ score almost doubled when they switched to Claude Code from their own harness. https://x.com/sayashk/status/1996334941832089732
Replies
withinboredom • yesterday at 2:07 PM
Which, IMHO, should be why we should be able to change them freely or make our own. Being locked into a specific harness because you pay 20 bucks per month vs. pay-per-use ... is kinda dumb.
➕ show 3 replies
Mario, the creator of Pi terminal agent, has this great blog post[0]. He talks about how TerminalBench's highest scores comes from using the Terminus 2 harness which uses tmux under the hood.
When I was reading the Opus 4.6 launch post, they mentioned the same thing and their TerminalBench score was based on using Terminus 2 and not CC.
0. https://mariozechner.at/posts/2025-11-30-pi-coding-agent/