GLM-5

Reasoning

Creator

Z AI

Released

2026-02-11

Intelligence

39.5

Artificial Analysis Index

Coding

Artificial Analysis Index

In $/1M

$1.00

input tokens

Out $/1M

$3.20

output tokens

Blended $/1M

$1.55

3:1 blended

Speed

0

tokens / sec

Profile

License, openness, and modality — the governance layer.

License

MIT

commercial OK

Weights

Open

downloadable

Modalities

Text

Parameters

744B

total

GLM-5 is Zhipu AI's flagship foundation model designed for complex system engineering and long-range Agent tasks, shifting focus from coding to engineering. It features 744B total parameters (40B activated) in a Mixture of Experts architecture, trained on 28.5T tokens. GLM-5 integrates DeepSeek Sparse Attention for higher token efficiency while preserving long-context quality. It supports 200K context length and 128K max output tokens, with capabilities including thinking modes, real-time streaming, function calling, context caching, and structured output. GLM-5 approaches Claude Opus 4.5 in code-logic density and systems-engineering capability.

Capability profile

Category strength across 20 domains, via LLM Stats.

search
80frontend development
80code
70agents
70
general
70reasoning
70tool calling
70
Via LLM Stats

Benchmark breakdown

Independent evaluation scores, normalized to 0–100.

GPQA Diamond
82
Humanity’s Last Exam
27
MMLU-Pro
SciCode
46
LiveCodeBench
MATH-500
AIME 2025
τ²-Bench (agentic)
98
Terminal-Bench Hard
43
IFBench
72
Via Artificial Analysis

Providers

Inference hosts serving this model — their own pricing and measured performance, cheapest input first.

ProviderIn $/1MOut $/1MThroughputLatencyStatus
FriendliAI$1.00$3.20active
ZAI$1.00$3.20303.00active
All providers

2 hosts · via LLM Stats

© 2026 NYSGPT2525 LLC