Back to BlogModel Launch · February 2026
Z.AI Frontier Model

GLM-5 is here

A 745B parameter open-source frontier model for engineering-grade agent work

Today we are launching GLM-5 on LeemerChat as the newest frontier addition in our Z.AI lineup. With 745B total parameters, advanced MoE architecture, and best-in-class performance among open-source models on reasoning, coding, and agentic tasks — GLM-5 narrows the gap with proprietary frontier systems.

Total Parameters

745B

Active Parameters

40-50B

Training Tokens

28.5T

Context Length

128K+

Frontier Open Source

Why GLM-5 matters

We believe scaling remains one of the strongest levers for improving intelligence efficiency on the path to AGI. But raw scale alone is not enough. What makes GLM-5 compelling is how pre-training scale, systems efficiency, and reinforcement learning infrastructure were advanced together.

GLM-5 represents a major step forward in open-weight AI systems. With approximately 745 billion total parameters and a Mixture-of-Experts (MoE) architecture that activates only 40-50 billion parameters per token, it delivers frontier-level performance with manageable computational costs.

The result is a model that pushes beyond GLM-4.7 on reasoning, coding, and agentic execution benchmarks, while narrowing the gap to top closed frontier systems like Claude Opus 4.5, Gemini 3 Pro, and GPT-5.2. Practically, this means better reliability in long tool chains, fewer collapses on multi-step objectives, and stronger completion quality under real production constraints.

Native Multimodal

Core Capabilities

GLM-5 is designed for complex systems engineering and long-horizon agentic tasks. It excels across reasoning, coding, and autonomous execution domains.

Complex Reasoning

Advanced mathematical reasoning, scientific analysis, and logical problem-solving at frontier level.

Code Intelligence

State-of-the-art software engineering, debugging, and multi-language code generation capabilities.

Agentic Execution

Long-horizon task planning, tool orchestration, and autonomous workflow execution.

Systems Engineering

End-to-end system design, architecture planning, and complex engineering workflows.

Terminal Operations

Advanced command-line operations, shell scripting, and infrastructure automation.

Long Context

Process massive documents, codebases, and multi-step reasoning chains efficiently.

Architecture

Technical Architecture

Mixture-of-Experts (MoE)

745B total parameters with only 40-50B active per token. Smart routing selects specialized experts for each input, maximizing capability while minimizing compute.

DeepSeek Sparse Attention

Advanced sparse attention mechanisms enable efficient long-context processing without proportional compute overhead. Handle 128K+ context windows with ease.

Async RL Infrastructure

New "slime" reinforcement learning system increases training throughput for faster iteration and improved post-training quality.

Scale-Up Training

Pre-training corpus expanded from 23T to 28.5T tokens. Total parameters scaled from 355B to 745B for broader coverage and stronger generalization.

Generation-over-Generation

GLM-5 vs GLM-4.7 Improvements

Significant gains across agentic, reasoning, and coding benchmarks demonstrate the impact of increased scale and improved post-training.

Humanity's Last Exam

+17.8%improvement
42.8%50.4%

Terminal-Bench 2.0

+37.1%improvement
41.0%56.2%

MCP-Atlas

+30.4%improvement
52.0%67.8%

CyberGym

+83.8%improvement
23.5%43.2%

Tool-Decathlon

+59.7%improvement
23.8%38.0%
Reasoning Benchmarks

Academic & Reasoning Performance

GLM-5 demonstrates strong performance across mathematical reasoning, scientific knowledge, and academic benchmarks — competitive with leading frontier models.

BenchmarkDescription
GLM-5
GLM-4.7
AnthropicClaude Opus 4.5
GoogleGemini 3 Pro
OpenAIGPT-5.2
DeepSeek-V3.2Kimi K2.5
Humanity's Last ExamAcademic reasoning benchmarkNo tools30.5%24.8%28.4%37.2%35.4%
Humanity's Last ExamWith tool access enabledWith tools50.4%42.8%43.4%45.8%45.5%
AIME 2026 IMathematics competition92.7%92.9%93.3%90.6%92.7%92.5%
HMMT Nov. 2025Harvard-MIT Math Tournament96.9%93.5%91.7%93.0%97.1%90.2%91.1%
IMO AnswerBenchInternational Math Olympiad82.5%82.0%78.5%83.3%86.3%78.3%81.8%
GPQA-DiamondGraduate-level science Q&A86.0%85.7%87.0%91.9%92.4%82.4%87.6%
Coding Benchmarks

Software Engineering Excellence

Top-tier performance on real-world coding tasks, from repository-level changes to terminal-based workflows and cybersecurity challenges.

BenchmarkDescription
GLM-5
GLM-4.7
AnthropicClaude Opus 4.5
GoogleGemini 3 Pro
OpenAIGPT-5.2
DeepSeek-V3.2Kimi K2.5
SWE-bench VerifiedReal-world software engineering77.8%73.8%80.9%76.2%80.0%76.8%
SWE-bench MultilingualCross-language code tasks73.3%66.7%77.5%65.0%72.0%73.0%
Terminal-Bench 2.0Agentic terminal workflows56.2%41.0%59.3%54.2%54.0%
CyberGymCybersecurity challenges43.2%23.5%50.6%39.9%17.3%41.3%
Agentic Benchmarks

Autonomous Agent Performance

Exceptional capability in multi-step planning, tool orchestration, and long-horizon task execution — key for production AI agents.

BenchmarkDescription
GLM-5
GLM-4.7
AnthropicClaude Opus 4.5
GoogleGemini 3 Pro
OpenAIGPT-5.2
DeepSeek-V3.2Kimi K2.5
BrowseCompWeb browsing & research75.9%67.5%67.8%59.2%65.8%74.9%
MCP-AtlasMulti-step MCP workflows67.8%52.0%65.2%66.6%68.0%
τ²-BenchAgentic tool use & planning89.7%87.4%91.6%90.7%85.5%
Tool-DecathlonLong-horizon real-world tasks38.0%23.8%43.5%36.4%46.3%35.2%27.8%
Head-to-Head Comparison

Key Benchmark Highlights

Visual comparison of GLM-5 against leading frontier models across critical benchmarks.

Reasoning

Humanity's Last Exam (with tools)

Score
GLM-550.4%
Gemini 3 Pro45.8%
GPT-5.245.5%
Claude Opus 4.543.4%
GLM-4.742.8%

Coding

SWE-bench Verified

Score
Claude Opus 4.580.9%
GPT-5.280%
GLM-577.8%
Gemini 3 Pro76.2%
GLM-4.773.8%

Agents

MCP-Atlas

Score
GPT-5.268%
GLM-567.8%
Gemini 3 Pro66.6%
Claude Opus 4.565.2%
GLM-4.752%

Terminal

Terminal-Bench 2.0

Score
Claude Opus 4.559.3%
GLM-556.2%
GPT-5.254%
Gemini 3 Pro54.2%
GLM-4.741%
Applications

Designed for Real-World Impact

GLM-5 excels in scenarios requiring deep reasoning, complex coding, and autonomous execution.

Software Engineering

Build, debug, and refactor complex codebases. Excel at SWE-bench tasks, multilingual coding, and long-horizon development workflows.

AI Agents & Automation

Deploy autonomous agents for research, data processing, and multi-step business workflows with reliable long-horizon execution.

Systems Architecture

Design distributed systems, cloud infrastructure, and complex technical architectures with deep reasoning capabilities.

Research & Analysis

Process massive documents, perform literature reviews, and synthesize insights across long-form content.

Specifications

Technical Specifications

Architecture

Mixture-of-Experts (MoE)

Total Parameters

~745 billion

Active Parameters

40-50 billion per token

Pre-training Data

28.5 trillion tokens

Context Window

128,000+ tokens

Attention Mechanism

DeepSeek Sparse Attention (DSA)

License

MIT (Open Source)

Inference Framework

vLLM compatible

Developer

Zhipu AI (Z.ai)

Advantages

Why Choose GLM-5?

Best-in-class performance among open-source models on reasoning benchmarks
Top-tier coding performance with 77.8% on SWE-bench Verified
Exceptional agentic capabilities with 67.8% on MCP-Atlas
Massive 745B parameter scale with efficient MoE architecture
MIT licensed — full commercial use, fine-tuning, and deployment freedom
Cost-efficient inference with only 40-50B active parameters per token
Native long-context support for complex document and codebase analysis
Strong multilingual capabilities across coding and reasoning tasks
Open Source

MIT Licensed — Full Freedom

GLM-5 is released under the MIT license, enabling commercial use, fine-tuning, and research deployment without restrictive licensing barriers. Build with confidence.

MIT

License

100%

Open Weight

What this unlocks in LeemerChat

  • Stronger model reliability for long-horizon engineering prompts
  • Better planning + execution in multi-tool, multi-turn agent loops
  • Higher quality code reasoning under multilingual and terminal-heavy tasks
  • A more capable open-source control brain for orchestrated workflows
  • Complex systems engineering with deep reasoning capabilities
  • Autonomous agent workflows with reliable long-horizon execution
Available now on LeemerChat

Experience the Frontier of Open Source

GLM-5 represents a new standard for open-weight AI. Best-in-class performance, MIT licensed, and ready for your most demanding engineering and agentic workflows.