Z.ai
Z.ai

GLM-5

Model ID:z-ai/glm-5
2026-02-11Open Model
API
OverallNo.4
PopularityNo.22

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 closed-source models. With advanced agentic planning, deep backend reasoning, and iterative self-correction, GLM-5 moves beyond code generation to full-system construction and autonomous execution.

Knowledge Cutoff
2026-02-17

The date this AI finished learning. It may not know about things that happened after this date.

Input → Output Format

The types of content this AI can receive, and what it can produce in return.

Context Memory
80KIN131KOUT

The maximum amount of text the AI can read and process in a single request. A larger number means it can handle longer documents or conversations.

Cost/1M Words
$0.72IN$2.3OUT

The cost of using this AI directly in your own application. Shown in USD per 1 million units of text (tokens).

AI Performance Evaluation

Arena Overall Score
1455
±6
As of 2026-04-02
Overall Rank
No.22
12,564 Votes
Arena by Ability
Hard Prompts
1477±7No.26
Expert Knowledge
1489±20No.20
Instruction Following
1448±10No.24
Conversation Memory
1458±13No.31
Creative
1443±14No.18
Coding
1491±11No.35
Math
1457±20No.20
Arena by Occupation
Creative Writing
1440±11No.23
Social Sciences
1488±14No.9
Media
1430±12No.26
Business
1447±12No.32
Healthcare
1501±20No.9
Legal
1469±19No.21
Software
1484±9No.31
Mathematics
1468±23No.18
Reasoning Ability
AA Intelligence Index
50%↑11%
GPQA Diamond
82%↑0%
HLE
27%↑11%
Coding Ability
AA Coding Index
44%↑8%
SciCode
46%↑4%
TerminalBench
43%↑9%
Instruction Following
IFBench
72%↑15%
Long Context
AA-LCR
63%↑0%
Agentic AI Ability
TAU2
98%↑27%
Speed
Standard Mode
53tok/sec↓25
First Output 1.29s
Artificial Analysis
Reasoning Mode
65tok/sec↓8
First Output 48.66s
Artificial Analysis