Benchmark Coding Agents Llm Serving Open Source App-building workflows Local Inference

GLM

Z.ai's flagship language model family

GLM is Z.AI's family of large language models, spanning named GLM generations and releases for text generation, reasoning, and agentic/coding use cases.

Pricing

Official site · Sep 8, 2026, 1:10 PM

Input / 1M

$1.40

Output / 1M

$4.40

Cached input / 1M

$0.26

Prices per 1M tokens for GLM-5.3. Other GLM releases have different prices; cached-input storage is listed as limited-time free.

Z.AI’s official pricing page does not list an unversioned “GLM” SKU; it lists individual GLM releases. This finding uses the currently listed GLM-5.3 release as the applicable current GLM price, rather than treating prices as universal across all GLM versions.

View source

Model Intelligence

Arena ranking

Benchmarkable

Model level

family

Intelligence Index

25.1

Math Index

MMLU Pro

0.83

GPQA

0.78

HLE

0.13

LiveCodeBench

0.7

SciCode

0.38

AIME 2025

0.86

IFBench

0.43

LCR

0.54

TerminalBench Hard

0.25

TAU2

0.7

Recent stories

1 linked story

newsPRIMARY2026-06-20

GLM 5.2 claims 1M-token local coding as builders compare it with Opus 4.8

Builders across X described GLM 5.2 as a surprisingly capable local coding model, citing MIT licensing, a 1M-token context window, and experiments on desktop or distributed GPU setups. The shift matters because it reopens local-first website and code workflows for vibe coders, though hardware cost and throughput still lag cloud subscriptions.