Grok 4.3
SpaceXAI · 4 thinking configurations
Intelligence24.9
Input / 1M$1.25
Output / 1M$2.50
Context1M
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 · 2 without both values
Selected: thinking high · Click a point to switch configuration
Grok 4.3 is a reasoning model from SpaceXAI. It accepts text and image inputs with text output, and is suited for agentic workflows, instruction-following tasks, and applications requiring high factual...
Intelligence IndexArtificial Analysis composite index, not a percentage. Different versions of the index are not directly comparable.
24.9 pointsGPQA DiamondGraduate-level scientific questions. Measures specialist reasoning rather than web-search quality.
90.1 %Humanity’s Last ExamDifficult questions across many disciplines, compared under the same evaluation setup.
37.2 %SciCodeCode generation for scientific research problems.
48.3 %Terminal-Bench 2.1Agent tasks in a terminal environment. Results also depend on the evaluation harness.
39.7 %τ²-BenchTool use and interaction in assistance scenarios. Does not replace an evaluation of your integration.
97.7 %IFBenchVerifiable instruction following. A proxy for precision rather than a benchmark of creative style.
81.3 %MMMU-ProMultimodal understanding of academic problems that include images.
78.1 %Omniscience accuracyFactual accuracy in Artificial Analysis's Omniscience evaluation.
34.8 %Specifications from the catalog
Inputtext, image, file
Outputtext
Tool callingYes
Structured outputYes
Speed110.9 tok/s
First token28.69 s
Maximum output900K
Catalog listing date2026-04-30