GLM-5.2
Z AI · 3 thinking configurations
Intelligence33.7
Input / 1M$1.40
Output / 1M$4.40
Context1M
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 cost1 measured configurations · 2 without both values
Selected: thinking max · Click a point to switch configuration
GLM 5.2 is a large-scale reasoning model from Z.ai. It supports text input and output with a 1M-token context window, and is suited for long-horizon agent workflows, project-level software engineering,...
Intelligence IndexArtificial Analysis composite index, not a percentage. Different versions of the index are not directly comparable.
33.7 pointsDeepSWE · pass@1Software-engineering tasks on mini-swe-agent v1.1. Pass@1 across evaluated runs, with measured cost per task. The 95% intervals may overlap.
43.8 % ±1.7GPQA DiamondGraduate-level scientific questions. Measures specialist reasoning rather than web-search quality.
89.5 %Humanity’s Last ExamDifficult questions across many disciplines, compared under the same evaluation setup.
41.1 %SciCodeCode generation for scientific research problems.
51.2 %Terminal-Bench 2.1Agent tasks in a terminal environment. Results also depend on the evaluation harness.
77.9 %τ²-BenchTool use and interaction in assistance scenarios. Does not replace an evaluation of your integration.
99.1 %IFBenchVerifiable instruction following. A proxy for precision rather than a benchmark of creative style.
73.3 %Omniscience accuracyFactual accuracy in Artificial Analysis's Omniscience evaluation.
24.3 %Specifications from the catalog
Inputtext
Outputtext
Tool callingYes
Structured outputYes
Speed78.8 tok/s
First token3.12 s
Maximum output943.7K
Catalog listing date2026-06-16
DeepSWE v1.1 · 113 tasks · mini-swe-agent · cost $3.92 / task · 129 mean steps · 78.2K mean output tokens. Published by the source 9/22/2026.