xAI · LIVEBENCH 2026-06-25

Grok 4.6 xHigh

Published benchmark results for this specific model configuration.

grok-4.6

Overall score78.0 / 100

Cost / successful task$0.207USD · benchmark workload

Weight accessNot reported

Where this configuration performs

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

Reasoning90.5

Coding76.8

Agentic Coding57.0

Mathematics92.6

Data Analysis73.9

Language83.7

Instruction Following71.9

Task-level results

theory of mind86.5zebra puzzle95.5spatial98.0logic with navigation82.0code generation77.5code completion76.1javascript72.7typescript43.3python55.0AMPS Hard97.0integrals with game85.0math comp97.1olympiad91.2consecutive events78.1tablejoin43.4tablereformat100.0connections100.0plot unscrambling67.1typos84.0paraphrase71.8simplify69.3story generation78.3summarize68.1

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