Grok 4.5 benchmarks

Grok 4.5 is a proprietary model from xAI, released 8 Jul 2026. It ranks 31st of 51 on our overall leaderboard and 17th of 41 for agents. At A$4.21 per million tokens (blended), it costs 1.2× the median model we track. None of the major cloud platforms offer it in an Australian region yet.

#31 OF 51 OVERALLA$4.21 / 1M TOKENS500K CONTEXTUPDATED 23 SEP 2026
CONTEXT WINDOW
500,000 tokens
INPUT
text, image
WEIGHTS
Proprietary
RELEASED
8 Jul 2026
XAI DOCS
§ 02 — RESULTS

Benchmark results.

Independent test scores are for the high effort setting. “Among tracked” ranks Grok 4.5 against the 51 models on this site; LMArena ranks run across its full leaderboard.

ALL RESULTS7 OF 8 CORE SIGNALS
Grok 4.5 benchmark results
BENCHMARKRESULTAMONG TRACKEDSOURCE DETAIL
INDEPENDENT TESTS · ARTIFICIAL ANALYSIS
AA Intelligence Index38.8#26 of 51high effort
AA Coding Index72.4#18 of 42high effort
GPQA Diamond93.1%#12 of 44high effort
Humanity’s Last Exam42.7%#24 of 51high effort
AA-LCR79.3%#34 of 51high effort
Terminal-Bench 2.181.6%#19 of 42high effort
τ²-Bench (banking)42.1%#12 of 41high effort
SciCode55.0%#21 of 46high effort
BLIND HUMAN VOTES · LMARENA
LMArena Text30,103 votes · ±51468#28 of 42#42 of 402 on LMArena · 13 Sep 2026
LMArena WebDev10,137 votes · ±71552#23 of 45#28 of 129 on LMArena · 22 Sep 2026
LMArena Vision8,355 votes · ±81280#19 of 33#24 of 152 on LMArena · 13 Sep 2026
LMArena Document4,965 votes · ±91464#17 of 26#22 of 44 on LMArena · 13 Sep 2026
LMArena Search31,505 votes · ±71202#7 of 12#8 of 34 on LMArena · 24 Aug 2026
LMArena Agent38,146 sessions#19#17 of 37#19 of 46 on LMArena · 15 Sep 2026
§ 03 — COST

What Grok 4.5 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 4.5 price per million tokens
PER MILLION TOKENSAUDUSD LIST
Input tokensA$2.81US$2.00
Output tokensA$8.42US$6.00
Blended (3 in : 1 out)A$4.21US$3.00
EVERYDAY JOBSESTIMATES
Estimated cost of common jobs in Australian dollars
JOBCOST (AUD)MEDIAN MODEL
Customer support replyPER 1,000 REPLIESA$8.14A$6.58
Summarise a 30-page documentPER 100 DOCUMENTSA$6.29A$4.74
Agentic coding taskPER 10 TASKSA$4.89A$3.72
§ 04 — AUSTRALIA

Running Grok 4.5 in Australia.

None of the major cloud platforms offer it in an Australian region yet. How the platforms compare →

AUSTRALIAN CLOUD REGIONS
Grok 4.5 availability in Australian cloud regions
PLATFORMAVAILABILITYDETAIL
AWS Bedrock · SydneyNOT OFFERED
AWS Bedrock · MelbourneNOT OFFERED
Azure · Australia EastNOT OFFERED
Google Vertex AI · SydneyNOT OFFERED
§ 06 — QUESTIONS

Grok 4.5, answered.

Grok 4.5 lists at US$2.00 per million input tokens and US$6.00 per million output tokens — A$2.81 and A$8.42 at A$1 = US$0.7123 (RBA, 22 Sep 2026), excluding GST. A typical customer support reply works out at about A$8.14 per 1,000 replies, before any reasoning tokens.

None of the major cloud platforms offer it in an Australian region yet. Availability comes from the cloud providers’ own documentation; check your provider’s current terms before relying on it for data-residency obligations.

It ranks 19th of 42 on our coding ranking, with an Artificial Analysis Coding Index of 72.4 and an LMArena WebDev rating of 1552 (28th of 129). The current leader is Claude Fable 5.1.

It ranks 17th of 41 on our agents ranking, completing 42.1% of τ²-Bench banking customer-service tasks and 81.6% of Terminal-Bench 2.1 tasks.

xAI documents a context window of 500,000 tokens (500K). On AA-LCR, which tests reasoning across ~100,000-token document sets, it scores 79.3%.

PUT THE COMPARISON TO WORK

Need help choosing and using AI for your business?