Pick Kimi K2.6 for long-horizon local coding agents: 4,000+ tool calls over a 13-hour run

Atlas Cloud·medium signal

For self-hosted autonomous coding, Kimi K2.6 (open weights) scores 66.7% on Terminal-Bench 2.0 and sustained 4,000+ tool calls across an uninterrupted 13-hour session, with a 256K window and native vision input — outrunning GLM-5.1 on agentic tasks despite a near-tie on SWE-bench Pro. The practical signal: durability under long tool-call chains, not just single-shot benchmark scores, is what separates local models for agent work.