GLM-4.7, your new coding partner, is coming with the following features:

• Core Coding: GLM-4.7 brings clear gains, compared to its predecessor GLM-4.6, in multilingual agentic coding and terminal-based tasks, including (73.8%, +5.8%) on SWE-bench, (66.7%, +12.9%) on SWE-bench Multilingual, and (41%, +16.5%) on Terminal Bench 2.0. GLM-4.7 also supports thinking before acting, with significant improvements on complex tasks in mainstream agent frameworks such as Claude Code, Kilo Code, Cline, and Roo Code.
• Vibe Coding: GLM-4.7 takes a major step forward in UI quality. It produces cleaner, more modern webpages and generates better-looking slides with more accurate layout and sizing.
• Tool Using: GLM-4.7 achieves significantly improvements in Tool using. Significant better performances can be seen on benchmarks such as τ^2-Bench and on web browsing via BrowseComp.
• Complex Reasoning: GLM-4.7 delivers a substantial boost in mathematical and reasoning capabilities, achieving (42.8%, +12.4%) on the HLE (Humanity’s Last Exam) benchmark compared to GLM-4.6.

You can also see significant improvements in many other scenarios such as chat, creative writing, and role-play scenario.

Benchmark Performance. More detailed comparisons of GLM-4.7 with other models GPT-5, GPT-5.1-High, Claude Sonnet 4.5, Gemini 3.0 Pro, DeepSeek-V3.2, Kimi K2 Thinking, on 17 benchmarks (including 8 reasoning, 5 coding, and 3 agents benchmarks) can be seen in the below table.

Coding: AGI is a long journey, and benchmarks are only one way to evaluate performance. While the metrics provide necessary checkpoints, the most important thing is still how it *feels*. True intelligence isn't just about acing a test or processing data faster; ultimately, the success of AGI will be measured by how seamlessly it integrates into our lives-"coding" this time.

Interleaved Thinking & Preserved Thinking

GLM-4.7 enhances Interleaved Thinking, a feature introduced since GLM-4.5, and further introduces Preserved Thinking and Turn-level Thinking. By thinking between actions and staying consistent across turns, it makes complex tasks more stable and more controllable:

• Interleaved Thinking: GLM-4.7 thinks before every response and tool calling, improving instruction following and the quality of generation.
• Preserved Thinking: In coding agent scenarios, GLM-4.7 automatically retains all thinking blocks across multi-turn conversations, reusing the existing reasoning instead of re-deriving from scratch. This reduces information loss and inconsistencies, and is well-suited for long-horizon, complex tasks.
• Turn-level Thinking: GLM-4.7 supports per-turn control over reasoning within a session—disable thinking for lightweight requests to reduce latency/cost, enable it for complex tasks to improve accuracy and stability.

More details: https://docs.z.ai/guides/capabilities/thinking-mode

Call GLM-4.7 API via Z.ai API platform

The Z.ai API platform offers the GLM-4.7 model. For comprehensive API documentation and integration guidelines, please refer to https://docs.z.ai/guides/llm/glm-4.7. At the same time, the model is also available worldwide through OpenRouter (https://openrouter.ai/).

Use GLM-4.7 with Coding Agents

GLM-4.7 is now available to use within coding agents (Claude Code, Kilo Code, Roo Code, Cline and more).

For GLM Coding Plan subscribers: You'll be automatically upgraded to GLM-4.7. If you've previously customized the app configs (like ~/.claude/settings.json in Claude Code), simply update the model name to "glm-4.7" to complete the upgrade.

For New users: Subscribing GLM Coding Plan means having access to a Claude-level coding model at a fraction of the cost — just 1/7th the price with 3x the usage quota. Start building today: https://z.ai/subscribe.

Chat with GLM-4.7 on Z.ai

GLM-4.7 is accessible through Z.ai. Try to change the model option to GLM-4.7, if the system does not automatically do that (not like an AGI in that case :))

Serve GLM-4.7 Locally

Model weights for GLM-4.7 are publicly available on HuggingFace and ModelScope. For local deployment, GLM-4.7 supports inference frameworks including vLLM and SGLang. Comprehensive deployment instructions are available in the official GitHub repository.

Footnotes

1: Default settings (most tasks): temperature 1.0, top-p 0.95, max new tokens 131072. For multi-turn agentic tasks (τ²-Bench and Terminal Bench 2), enable Preserved Thinking mode.

2: Terminal Bench and SWE-bench Verified settings: temperature 0.7, top-p 1.0, max new tokens 16384.

3: τ²-Bench settings: temperature 0, max new tokens 16384. For τ²-Bench, we added an extra prompt in the Retail and Telecom interactions to avoid failures caused by users ending the interaction incorrectly; for the Airline domain, we applied the domain fixes proposed in the Claude Opus 4.5 release report.