The first results for Terminal Bench 2.1, all 89 tasks, 3 iterations. Our ~1,300 lines…
This is a AI post classified by AGK Intelligence as AI coding agents (a model release), kept by the AI Radar because it carries real work, not commentary.
The first results for Terminal Bench 2.1, all 89 tasks, 3 iterations. Our ~1,300 lines Mini Harness landed in the middle of the pack, while being the fastest. In progress: OpenCode, Terminus 2, mini-swe-agent.
Posted by Paweł Huryn (135.4k followers) 8 h ago · 48 likes · 5.1k views · view the original post on X. Kept by the AI Radar as AI coding agents. Tools mentioned: mini-harness.
More AI work like this
- The Daytona Playbook: From $1M to $100M in a Year — @guilleflorvs
- Claude Code 2.1.318 对用 claude -p 挂定时任务的人很实用： — @wei_wang
- Here are 10 new AI agent skills for Claude Code, Codex and more — @shushant_l
- Can coding agents replace traditional 3D vision pipelines and build a entire interactive… — @EinsiaAI
- Nous just shipped an official Security plugin for Hermes… it reviews a local repo on the… — @HermesAgentTips
- The best tool for an AI agent is a markdown previewer. — @mfranz_on
- 🚀 Work across multiple agents, keep your favorite canvases close, and customize how you… — @code
- Bring your existing coding agent configuration to Command Code. — @CommandCodeAI
Every post is read and classified by AGK Intelligence: what it is, which market it belongs to, and whether the link is a real tool. 65.6k posts from 5k X accounts over the last 14 days, 10.4k tools, 19 markets. New posts are collected several times an hour and the full ranking is recomputed every hour — last update 2026-11-06 16:05 UTC. Full method.