Macaron-V1 adds a coding checkpoint and 1M-context support on GLM-5.2
kristoph · x · 2026-07-27
Macaron-V1 is out with a new Coding-Venti checkpoint aimed at standalone coding workflows.
- The quoted announcement says the model is based on GLM-5.2.
- It reports leading scores on five benchmarks, including 87.6 on TerminalBench 2.1 and 87.8 on UI4ABench.
- Both variants support a 1M token context window.
- Macaron-V1-Venti is positioned for long-horizon agents and GenUI, while Coding-Venti merges the coding specialist for standalone deployment across Chat, Agent, Coding, and GenUI.
- The release is MIT licensed, subject to base-model and serving-dependency requirements.
More from coding & agent
- Moonshot open-sources AgentENV, a distributed platform for large-scale agent training — teortaxesTex · 2026-07-27
- New study says agent skills should be judged by regressions, not just average gains — omarsar0 · 2026-07-27
- A Claude Opus 5 prompt reportedly built a playable birthday game in a 21-hour run — mattshumer_ · 2026-07-27
- A new skill cuts Claude.md clutter by 50% and audits agent instructions — iamrobotbear · 2026-07-27
- Anthropic ships a beta security plugin for Claude Code with multi-agent scans — thione · 2026-07-27
- Poolside releases Laguna S 2.1, an open-weight coding model with 1M context — thione · 2026-07-27