Z.ai: GLM 5

Z.ai: GLM 5

z-ai · Released Feb 11, 2026 Professional
Intelligence #14 / 590
82.0 Our Score
Speed #180 / 278
66.9 tokens / sec
Input #399 / 590
$0.600 per 1M tokens
Output #389 / 590
$1.92 per 1M tokens
Context #201 / 590
202,752 tokens

Analysis Summary

GLM 5 from Z.ai is a capable model with an intelligence index of 39.5 and a standout agentic index of 70.7, Tool use, function calling, a 202K context window, and strong instruction following (IFBench 0.723) make it well-suited to agentic pipelines and structured automation. The tau2 of 0.982 is one of the highest in the field, indicating very reliable task completion.

For businesses, GLM 5 is a strong fit for autonomous agent workflows, long-document processing, and structured data extraction. Pricing at $0.60 input and $1.92 output is competitive for its capability level. The main consideration is provider accessibility for teams outside Z.ai's primary markets, which may affect enterprise integration and support.

A compelling option for agentic and tool-use workloads where the provider relationship can be established, offering near-top-tier agentic performance at a fraction of flagship pricing.

Assessed June 30, 2026

Editorial notes

Z.ai GLM 5 delivers a strong agentic index of 70.7 and intelligence index of 39.5 with tool use and a 202K context at $0.60 input, though it carries a provider accessibility penalty.

Rankings consider pricing, capabilities, benchmarks, and real-world applicability and are refreshed as new models launch. Feedback?

Performance Profile

Intelligence5.9Technical8.7Value7.5Content7.7
Intelligence 5.9/10
Technical 8.7/10
Content 7.7/10
Value 7.5/10

How Z.ai: GLM 5 compares

Z.ai: GLM 5 ranks #36 of 385 AI models we track for overall intelligence, #13 of 293 for agentic tasks. Its 203K-token context window is larger than 66% of the models we list. At $0.60 per million input tokens it is cheaper than 32% of comparable models.

About Z.ai: GLM 5

GLM-5 is Z.ai’s flagship open-source foundation model engineered for complex systems design and long-horizon agent workflows. Built for expert developers, it delivers production-grade performance on large-scale programming tasks, rivaling leading..

Capabilities

Tool Use Function Calling

Performance Indices

Source: Artificial Analysis

39.5 Intelligence Index
70.7 Agentic Index

Benchmark Scores

Intelligence

GPQA Diamond 82% Graduate-level scientific reasoning
HLE 27.2% Humanity's Last Exam
SciCode 46.2% Scientific computing

Technical

TerminalBench Hard 43.2% Agentic terminal tasks
τ²-Bench 98.2% Conversational agent benchmark

Content

IFBench 72.3% Instruction following
LCR 63.3% Long-context reasoning

Benchmark data from Artificial Analysis and Hugging Face

How does Z.ai: GLM 5 stack up?

Compare side-by-side with other professional models.

Compare Models

Model Information

OpenRouter ID z-ai/glm-5
Providerz-ai
Release Date February 11, 2026
Context Length202,752 tokens
Status Active

Pricing

Token Type Cost per 1M tokens Cost per 1K tokens
Input $0.60 $0.000600
Output $1.92 $0.001920

Live Performance

Live endpoint metrics, refreshed every 30 minutes.

98.2%
Avg Uptime
671ms
Best Latency (TTFT)
100 tok/s
Best Throughput
14/15
Active Endpoints
Available via: GMICloud, DeepInfra, StreamLake, Baidu, DigitalOcean, SiliconFlow, Chutes, AtlasCloud +7 more

Leaderboard Categories

Frequently asked questions about Z.ai: GLM 5

How much does Z.ai: GLM 5 cost?

Z.ai: GLM 5 costs $0.60 per million input tokens and $1.92 per million output tokens.

What is the context window of Z.ai: GLM 5?

Z.ai: GLM 5 has a context window of 202,752 tokens (203K).

What can Z.ai: GLM 5 do?

Z.ai: GLM 5 supports tool use and function calling.

Who created Z.ai: GLM 5?

Z.ai: GLM 5 is developed by Z.ai and was released on February 11, 2026.