GLM-4.6
Z AI · 2 thinking configurations
Intelligence18.5
Input / 1M$0.55
Output / 1M$2.20
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 thinking · Click a point to switch configuration
Compared with GLM-4.5, this generation brings several key improvements: Longer context window: The context window has been expanded from 128K to 200K tokens, enabling the model to handle more complex...
Intelligence IndexArtificial Analysis composite index, not a percentage. Different versions of the index are not directly comparable.
18.5 pointsGPQA DiamondGraduate-level scientific questions. Measures specialist reasoning rather than web-search quality.
78.0 %Humanity’s Last ExamDifficult questions across many disciplines, compared under the same evaluation setup.
14.5 %Terminal-Bench 2.1Agent tasks in a terminal environment. Results also depend on the evaluation harness.
49.4 %τ²-BenchTool use and interaction in assistance scenarios. Does not replace an evaluation of your integration.
70.5 %IFBenchVerifiable instruction following. A proxy for precision rather than a benchmark of creative style.
43.4 %Omniscience accuracyFactual accuracy in Artificial Analysis's Omniscience evaluation.
26.9 %Specifications from the catalog
Inputtext
Outputtext
Tool callingYes
Structured outputYes
Speed31.1 tok/s
First token4.72 s
Maximum output16.4K
Catalog listing date2025-09-30