Download
GLM-4.7 is an advanced agent-oriented large language model designed as a high-performance coding and reasoning partner. It delivers significant gains over GLM-4.6 in multilingual agentic coding, terminal-based workflows, and real-world developer benchmarks such as SWE-bench and Terminal Bench 2.0. The model introduces stronger “thinking before acting” behavior, improving stability and accuracy in complex agent frameworks like Claude Code, Cline, and Roo Code. GLM-4.7 also advances “vibe coding,” producing cleaner, more modern UIs, better-structured webpages, and visually improved slide layouts. Its tool-use capabilities are substantially enhanced, with notable improvements in browsing, search, and tool-integrated reasoning tasks. Overall, GLM-4.7 shows broad performance upgrades across coding, reasoning, chat, creative writing, and role-play scenarios.
Features
- Delivers strong benchmark gains in agentic coding, including SWE-bench, SWE-bench Multilingual, and Terminal Bench 2.0
- Supports Interleaved Thinking, Preserved Thinking, and Turn-level Thinking for more stable, controllable multi-step reasoning
- Produces higher-quality front-end outputs with cleaner UI design, improved layouts, and more polished visuals
- Significantly improves tool usage and web browsing performance on benchmarks like τ²-Bench and BrowseComp
- Achieves a major boost in mathematical and complex reasoning, with large gains on Humanity’s Last Exam (HLE)
- Integrates seamlessly with modern agent frameworks and supports efficient inference via vLLM, SGLang, and FP8 deployments
Project Samples
