SpaceXAI

Grok 4.6 (High)

Released 2026-08-12 · Context 500K · Data snapshot 2026-10-22

Overall score

64.3

Ranked #10
Benchmark coverage
90.9%
20 third-party benchmarks
Context window
500K
tokens
Input price
$2.00
Cache read $0.50
Output price
$6.00
per million tokens
OpenRouter usage
#73
147.0B tokens/day

Prices converted at snapshot-day rate (USD/CNY 6.6761)

Dimension performance

Reasoning67.5
Human preference65.0
Office64.6
Coding63.2
Knowledge62.1
Above averageBelow averageAnchored at 50 (reference models’ average); every 15 points ≈ one standard deviation

Benchmark details

Coding5 items
LiveBench 2.0 · Coding89.1
AA Coding Indexmedium74.4
LiveBench 2.0 · Browser64
AA Agentic Indexmedium50.6
LiveBench 2.0 · Long Agentic40.7
Reasoning3 items
LiveBench 2.0 · Reasoning91.2
FrontierMath (Tiers 1-3)xhigh66
AA Intelligence Indexmedium42.8
Office9 items
LiveBench 2.0 · Research84.5
LiveBench 2.0 · Design79.8
LiveBench 2.0 · Data Analysis75.3
AA Economicsmedium53.1
AA Legalmedium49.4
AA Strategy & Opsmedium48.9
AA Finance & Accountingmedium46.5
AA Healthcare & Medicalmedium44.4
AA Engineeringmedium43.3
Knowledge2 items
GPQA Diamondhigh94
SimpleQA Verifiedhigh49.3
Human preference1 items
LMArena Human Blind Vote1455.4161

Multiple reasoning tiers of the same benchmark take the best value; raw scores have different scales and are not comparable across benchmarks.

Score trend

2026-10-202026-10-22
View daily data
2026-10-2264.3
2026-10-2164.3
2026-10-2064.3
Scores and prices come from third-party public data (Artificial Analysis / LMArena / OpenRouter). 50 is the reference models’ average; every 15 points ≈ one standard deviation. Prices are converted at snapshot-day rates and provided for reference only. Return to LLM Leaderboard.