Grok 4.6 (xhigh)

ModelActive

by xAI · family “grok-xhigh”

Epoch Capabilities Index

Not scored by Epoch AI

Released

12 Aug 2026

Context window

Unknown

Max output

Unknown

Input $ / 1M tokens

Unknown

Output $ / 1M tokens

Unknown

Cached input $ / 1M

Unknown

Each benchmark shown separately with its own source

Benchmark results (14)

All benchmarks

Benchmark	Domain	Score	vs best recorded	Setting	Run	Source
Furniture Assembly	multimodal	40.0% ±6.3	48%	xhigh	24 Sep 2026	Epoch ↗
LMCA	agents	48.5%	74%	xhigh	—	External ↗
DTBench	reasoning	97.3%	99%	xhigh	—	External ↗
Mystery Game Puzzles	games	34.0% ±4.8	40%	xhigh	14 Aug 2026	Epoch ↗
EBR-bench	reasoning	30.5% ±1.6	40%	xhigh	18 Aug 2026	Epoch ↗
FrontierMath-Tiers-1-3-v2-Private	math	66.0% ±2.8	70%	xhigh	14 Aug 2026	Eval log ↗
FrontierMath-Tier-4-v2-Private	math	31.7% ±7.4	32%	xhigh	14 Aug 2026	Eval log ↗
DeepSWE	coding	66.7%	90%	xhigh	—	External ↗
Chess Puzzles	games	31.0% ±4.6	43%	xhigh	14 Aug 2026	Epoch ↗
SimpleQA Verified	knowledge	48.9% ±1.6	65%	xhigh	27 Aug 2026	Eval log ↗
ARC-AGI-2	reasoning	67.1%	71%	xhigh	—	External ↗
OTIS Mock AIME 2024-2025	math	99.2% ±0.5	99%	xhigh	14 Aug 2026	Epoch ↗
GPQA diamond	science	93.2% ±1.5	97%	xhigh	14 Aug 2026	Epoch ↗
ARC-AGI	reasoning	87.0%	88%	xhigh	—	External ↗

Source: Epoch AI Benchmarking Hub (CC BY 4.0). “External” rows are leaderboard results Epoch collects from third parties. Best reported setting per benchmark is shown.

API list price over time