Tag
agentic coding
Agentic coding refers to models that plan, edit, test, and iterate across a software task instead of answering a single prompt. It raises practical issues around tool use, multi-agent coordination, long contexts, token cost, and deployment choices for SWE-bench-style workflows and Claude Code-like setups.
8 articles
Why Xiaomi’s MiMo-V2.5-Pro Changes Coding Agents More Than Chatbots
MiMo-V2.5-Pro matters because it is built for long, tool-heavy coding work, not chat.
Kimi K2.6 and Qwen 3.6 Narrow the Gap
Kimi K2.6 and Qwen 3.6 are open-weight models that now rival closed models on coding and agent tasks.
AI Coding Agents Burn 1000x More Tokens Than Chat
A study of SWE-bench Verified shows agentic coding can consume 1000x more tokens than chat, with costs driven by inputs and hard to predict.
Qwen3.6-27B opens a smaller, sharper path to coding
Qwen3.6-27B is a 27B dense multimodal model that beats Qwen3.5-397B-A17B on key coding benchmarks while staying easier to deploy.
Claude Opus 4.7 发布：更会干活了
Anthropic发布Claude Opus 4.7，长任务、视觉理解和代码工作流更强，但Token消耗也更高。
Qwen3.6-35B-A3B: 35B Open Source Model Release
Qwen3.6-35B-A3B ships with 35B total params, 3B active params, and Anthropic API compatibility for Claude Code workflows.
Cursor Composer 2 Bets on Agentic Coding
Cursor’s Composer 2 posts 61.3 on CursorBench and 61.7 on Terminal-Bench 2.0, with pricing aimed at high-volume coding teams.
Xiaomi MiMo-V2-Pro: 1T MoE Model for Agents
Xiaomi’s MiMo-V2-Pro packs 1T parameters, 42B active, and 1M context, with SWE-bench results close to Claude Sonnet 4.6.