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

GLM

The GLM Large Models

GLM is Z.AI's large language/foundation model family. The text-model line includes releases such as GLM-5.2, GLM-5.1, GLM-5, GLM-4.7, GLM-4.6, and GLM-4.5, with capabilities focused on long-context work, coding, reasoning, tool use, and agentic engineering.

Pricing

Model profile · Current snapshot

Input / 1M

$0.60

Output / 1M

$2.20

Blended / 1M

$1.00

Output TPS

TTFT (s)

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.