GLM-5 is a new model from Z.ai designed for complex system engineering and long-range Agent tasks, with deep-reasoning performance in backend architecture, algorithms, and bug fixing. It benchmarks against Claude Opus 4.5 and integrates DeepSeek Sparse Attention for token efficiency.

New model

How it measures

Artificial Analysis · Intelligence Index · Reasoning

27.9141stof 696 models

Median 12.5Top 57.6

Benchmarks, as Artificial Analysis ran them

82%GPQA Diamond
29%Humanity's Last Exam
43%Terminal-Bench Hard
98%τ²-Bench
72%IFBench
76%Long context reasoning

Per 1M tokens: $1.00 in · $3.20 out
Context: 205K tokens

LMArena · Text65thof 416· 12th of 226 open models

1Gemini 4 Argon (High)
2Muse Wonder (Max)
3Claude Opus 5.5 (High)
4Claude Fable 5 (High)

glm-5 · 1,457 (1,453–1,462) · 29,272 votes

Rated by versionGLMRated 16 points above GLM-4.7; GLM-5.3 rates 21 points higher.

GLM-5 · 1,457 (1,453–1,462) · 65th

Against list priceRating for the price

GLM-5 · 1,457 · $1.55 per 1M tokens ($1.00 in, $3.20 out) · 205K context

LMArena, CC BY 4.0, 15 October 2026 · prices OpenRouter, list price blended 3:1, read 21 October 2026 · Artificial Analysis, read 21 October 2026

About the model

Lab: Z.ai
Variant: GLM-5-Turbo
Weights: Open
Released: 12 February 2026, per models.dev
OpenRouter: Listed 11 February 2026z-ai/glm-5

Ask your AI

Your brief, straight from the record

Connect once, then ask Claude or ChatGPT what changed for the tools you use. Every item links to its page on forck.live.

+ any MCP app

Connect your AI →