xAI · LIVEBENCH 2026-06-25

Grok 4.3

Published benchmark results for this specific model configuration.

grok-4.3

Overall score62.2 / 100

Cost / successful task$0.061USD · benchmark workload

Weight accessNot reported

Where this configuration performs

Category averages from the same release, on a 0–100 scale.

Reasoning70.8

Coding69.9

Agentic Coding18.5

Mathematics84.3

Data Analysis55.8

Language73.6

Instruction Following62.8

Task-level results

theory of mind61.5zebra puzzle57.8spatial98.0logic with navigation66.0code generation74.6code completion65.2javascript27.3typescript13.3python15.0AMPS Hard97.0integrals with game63.0math comp95.1olympiad82.3consecutive events28.0tablejoin41.3tablereformat98.0connections94.0plot unscrambling48.7typos78.0paraphrase64.4simplify57.6story generation70.6summarize58.4

Source files: Scores ↗ Categories ↗ Costs ↗ . Missing cost is unknown, never free. Compare configurations within the same release.