Grok 4
SpaceXAI · 1 configuration
Intelligence22.5
Input / 1M$3.00
Output / 1M$15.00
Context256K
Tariff: SpaceXAI · 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 · 0 without both values
Selected: thinking thinking · Click a point to switch configuration
Grok model for agentic tool use, reasoning, coding, and live assistance
Intelligence IndexArtificial Analysis composite index, not a percentage. Different versions of the index are not directly comparable.
22.5 pointsGPQA DiamondGraduate-level scientific questions. Measures specialist reasoning rather than web-search quality.
87.7 %Humanity’s Last ExamDifficult questions across many disciplines, compared under the same evaluation setup.
26.7 %τ²-BenchTool use and interaction in assistance scenarios. Does not replace an evaluation of your integration.
74.9 %IFBenchVerifiable instruction following. A proxy for precision rather than a benchmark of creative style.
53.7 %MMMU-ProMultimodal understanding of academic problems that include images.
68.8 %Omniscience accuracyFactual accuracy in Artificial Analysis's Omniscience evaluation.
40.5 %Specifications from the catalog
Inputtext, image
Outputtext
Tool callingYes
Structured outputNo
SpeedNot available
First tokenNot available
Maximum output128K
Catalog listing date2025-07-10