Grok 4.20 0309
SpaceXAI · 2 thinking configurations
Intelligence14.6
Input / 1M$2.00
Output / 1M$6.00
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 none · Click a point to switch configuration
Intelligence IndexArtificial Analysis composite index, not a percentage. Different versions of the index are not directly comparable.
14.6 pointsGPQA DiamondGraduate-level scientific questions. Measures specialist reasoning rather than web-search quality.
78.5 %Humanity’s Last ExamDifficult questions across many disciplines, compared under the same evaluation setup.
24.5 %τ²-BenchTool use and interaction in assistance scenarios. Does not replace an evaluation of your integration.
69.6 %IFBenchVerifiable instruction following. A proxy for precision rather than a benchmark of creative style.
47.8 %MMMU-ProMultimodal understanding of academic problems that include images.
64.0 %Omniscience accuracyFactual accuracy in Artificial Analysis's Omniscience evaluation.
26.1 %Specifications from the catalog
Inputtext
Outputtext
Tool callingNot available
Structured outputNot available
SpeedNot available
First tokenNot available
Maximum output—
Catalog listing dateNot available