Grok 4.20 0309 v2
SpaceXAI · 2 thinking configurations
Intelligence25.7
Input / 1M$1.25
Output / 1M$2.50
Context2M
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 cost2 measured configurations · 0 without both values
Selected: thinking thinking · Click a point to switch configuration
Intelligence IndexArtificial Analysis composite index, not a percentage. Different versions of the index are not directly comparable.
25.7 pointsGPQA DiamondGraduate-level scientific questions. Measures specialist reasoning rather than web-search quality.
91.1 %Humanity’s Last ExamDifficult questions across many disciplines, compared under the same evaluation setup.
34.5 %τ²-BenchTool use and interaction in assistance scenarios. Does not replace an evaluation of your integration.
93.0 %IFBenchVerifiable instruction following. A proxy for precision rather than a benchmark of creative style.
81.2 %MMMU-ProMultimodal understanding of academic problems that include images.
74.6 %Omniscience accuracyFactual accuracy in Artificial Analysis's Omniscience evaluation.
27.5 %Specifications from the catalog
Inputtext
Outputtext
Tool callingNot available
Structured outputNot available
Speed101.5 tok/s
First token21.20 s
Maximum output—
Catalog listing dateNot available