Grok 4.6 benchmarks

Grok 4.6 is a proprietary model from xAI, released 12 Aug 2026. It ranks 34th of 54 on our overall leaderboard and 4th of 41 for agents. At A$4.32 per million tokens (blended), it costs about the same as the median model we track. It writes about 90 tokens a second, and answers start after 21 s on average, thinking included. It can be called from AWS Bedrock in Sydney and Melbourne, Microsoft Azure in Australia East and Google Vertex AI in Sydney, but only through global routing, so requests may be processed outside Australia.

#34 OF 54 OVERALLA$4.32 / 1M TOKENS500K CONTEXTUPDATED 2 OCT 2026
CONTEXT WINDOW
500,000 tokens
INPUT
text, image
WEIGHTS
Proprietary
RELEASED
12 Aug 2026
OUTPUT SPEED
90 tok/s
ANSWER STARTS AFTER
21 s (thinking included)
XAI DOCS ↗
§ 02 — RESULTS

Benchmark results.

Independent test scores are for the high effort setting. “Among tracked” ranks Grok 4.6 against the 54 models on this site; LMArena ranks run across its full leaderboard.

ALL RESULTS8 OF 8 CORE SIGNALS
Grok 4.6 benchmark results
BENCHMARKRESULTAMONG TRACKEDSOURCE DETAIL
INDEPENDENT TESTS · ARTIFICIAL ANALYSIS
AA Intelligence Index44.3#16 of 54high effort
AA Coding Index76.8#5 of 42high effort
GPQA Diamond94.9%#3 of 44high effort
Humanity’s Last Exam42.9%#25 of 54high effort
AA-LCR80.3%#26 of 54high effort
Terminal-Bench 2.188.4%#4 of 42high effort
τ²-Bench (banking)50.7%#1 of 41high effort
SciCode56.5%#19 of 49high effort
BLIND HUMAN VOTES · LMARENA
LMArena Text23,012 votes · ±51453#41 of 49#73 of 410 on LMArena · 30 Sep 2026
LMArena WebDev8,120 votes · ±81620#16 of 52#20 of 137 on LMArena · 30 Sep 2026
LMArena Vision5,374 votes · ±91263#29 of 36#39 of 156 on LMArena · 28 Sep 2026
LMArena Document2,258 votes · ±121461#19 of 26#24 of 44 on LMArena · 13 Sep 2026
LMArena Agent25,563 sessions#24#23 of 42#24 of 46 on LMArena · 30 Sep 2026
§ 03 — COST

What Grok 4.6 costs in Australian dollars.

List prices converted at the snapshot’s RBA rate, excluding GST. Reasoning models are billed for their thinking as output tokens, so heavier settings cost more than the job estimates show.

LIST PRICE
Grok 4.6 price per million tokens
PER MILLION TOKENSAUDUSD LIST
Input tokensA$2.88US$2.00
Output tokensA$8.63US$6.00
Blended (3 in : 1 out)A$4.32US$3.00
EVERYDAY JOBSESTIMATES
Estimated cost of common jobs in Australian dollars
JOBCOST (AUD)MEDIAN MODEL
Customer support replyPER 1,000 REPLIESA$8.35≈ A$8.20
Summarise a 30-page documentPER 100 DOCUMENTSA$6.45≈ A$5.35
Agentic coding taskPER 10 TASKSA$5.01≈ A$4.27
SETTINGSMEASURED SEPARATELY
Grok 4.6 settings compared
SETTINGINTELLIGENCEA$ / 1MSPEED
high effort44.3A$4.32
xhigh effort44.2A$4.32
medium effort42.8A$4.3290 tok/s
low effort35.1A$4.3264 tok/s
§ 04 — AUSTRALIA

Running Grok 4.6 in Australia.

It can be called from AWS Bedrock in Sydney and Melbourne, Microsoft Azure in Australia East and Google Vertex AI in Sydney, but only through global routing, so requests may be processed outside Australia. How the platforms compare →

AUSTRALIAN CLOUD REGIONS
Grok 4.6 availability in Australian cloud regions
PLATFORMAVAILABILITYDETAIL
AWS Bedrock · SydneyGLOBAL

Provider docs, checked 23 Sep 2026

AWS Bedrock · MelbourneGLOBAL

Provider docs, checked 23 Sep 2026

Azure · Australia EastGLOBAL

Provider docs, checked 23 Sep 2026

Google Vertex AI · SydneyGLOBAL

Provider docs, checked 23 Sep 2026

§ 06 — QUESTIONS

Grok 4.6, answered.

Grok 4.6 lists at US$2.00 per million input tokens and US$6.00 per million output tokens — A$2.88 and A$8.63 at A$1 = US$0.6949 (RBA, 1 Oct 2026), excluding GST. A typical customer support reply works out at about A$8.35 per 1,000 replies, before any reasoning tokens.

Grok 4.6 can be called from AWS Bedrock in Sydney and Melbourne, Microsoft Azure in Australia East and Google Vertex AI in Sydney, but only through global routing, so requests may be processed outside Australia. Availability comes from the cloud providers’ own documentation; check your provider’s current terms before relying on it for data-residency obligations.

It ranks 8th of 42 on our coding ranking, with an Artificial Analysis Coding Index of 76.8 and an LMArena WebDev rating of 1620 (20th of 137). The current leader is Claude Fable 5.1.

It ranks 4th of 41 on our agents ranking, completing 50.7% of τ²-Bench banking customer-service tasks and 88.4% of Terminal-Bench 2.1 tasks.

Artificial Analysis measures Grok 4.6 at about 90 tok/s of output, with the answer starting after 21 s on average once thinking time is included (high effort setting).

xAI documents a context window of 500,000 tokens (500K). On AA-LCR, which tests reasoning across ~100,000-token document sets, it scores 80.3%.

PUT THE COMPARISON TO WORK

Need help choosing and using AI for your business?