GLM-5
Z AI · 2 thinking configurations
Intelligence21.8
Input / 1M$1.00
Output / 1M$3.20
Context200K
Tariff: Z AI · Source: artificial-analysis · USD per million tokens
Thinking configuration
What does more thinking buy you?
Compare this model’s measured thinking configurations.
Scroll the chart ↔ · tap a point for details
Efficient frontier: best measured score at each cost2 measured configurations · 0 without both values
Selected: thinking none · Click a point to switch configuration
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...
Intelligence IndexArtificial Analysis composite index, not a percentage. Different versions of the index are not directly comparable.
21.8 pointsGPQA DiamondGraduate-level scientific questions. Measures specialist reasoning rather than web-search quality.
66.6 %Humanity’s Last ExamDifficult questions across many disciplines, compared under the same evaluation setup.
7.6 %τ²-BenchTool use and interaction in assistance scenarios. Does not replace an evaluation of your integration.
97.4 %IFBenchVerifiable instruction following. A proxy for precision rather than a benchmark of creative style.
55.2 %Omniscience accuracyFactual accuracy in Artificial Analysis's Omniscience evaluation.
23.1 %Specifications from the catalog
Inputtext
Outputtext
Tool callingYes
Structured outputYes
Speed71.8 tok/s
First token1.65 s
Maximum output128K
Catalog listing date2026-02-11