Claude Opus 4.6 benchmarks

Claude Opus 4.6 is a proprietary model from Anthropic, released 5 Feb 2026. It ranks 17th of 51 on our overall leaderboard and 22nd of 51 for long context. At A$14.04 per million tokens (blended), it costs 3.9× the median model we track. It can run with requests kept in Australia on AWS Bedrock in Sydney and Melbourne.

#17 OF 51 OVERALLA$14.04 / 1M TOKENS1M CONTEXTUPDATED 23 SEP 2026
CONTEXT WINDOW
1,000,000 tokens
MAX OUTPUT
128,000 tokens
INPUT
text, image
WEIGHTS
Proprietary
RELEASED
5 Feb 2026
ANTHROPIC DOCS
§ 02 — RESULTS

Benchmark results.

Independent test scores are for the adaptive reasoning, max effort setting. “Among tracked” ranks Claude Opus 4.6 against the 51 models on this site; LMArena ranks run across its full leaderboard.

ALL RESULTS5 OF 8 CORE SIGNALS
Claude Opus 4.6 benchmark results
BENCHMARKRESULTAMONG TRACKEDSOURCE DETAIL
INDEPENDENT TESTS · ARTIFICIAL ANALYSIS
AA Intelligence Index31.9#38 of 51Adaptive reasoning, max effort
GPQA Diamond89.6%#36 of 44Adaptive reasoning, max effort
Humanity’s Last Exam39.9%#34 of 51Adaptive reasoning, max effort
AA-LCR78.0%#41 of 51Adaptive reasoning, max effort
BLIND HUMAN VOTES · LMARENA
LMArena Text71,993 votes · ±41505#2 of 42#2 of 402 on LMArena · 13 Sep 2026
LMArena WebDev18,328 votes · ±61547#24 of 45#29 of 129 on LMArena · 22 Sep 2026
LMArena Vision20,835 votes · ±71299#4 of 33#5 of 152 on LMArena · 13 Sep 2026
LMArena Document27,929 votes · ±71495#2 of 26#2 of 44 on LMArena · 13 Sep 2026
LMArena Search134,699 votes · ±51223#4 of 12#4 of 34 on LMArena · 24 Aug 2026
§ 03 — COST

What Claude Opus 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
Claude Opus 4.6 price per million tokens
PER MILLION TOKENSAUDUSD LIST
Input tokensA$7.02US$5.00
Output tokensA$35.10US$25.00
Blended (3 in : 1 out)A$14.04US$10.00
EVERYDAY JOBSESTIMATES
Estimated cost of common jobs in Australian dollars
JOBCOST (AUD)MEDIAN MODEL
Customer support replyPER 1,000 REPLIESA$24.57A$6.58
Summarise a 30-page documentPER 100 DOCUMENTSA$16.85A$4.74
Agentic coding taskPER 10 TASKSA$13.34A$3.72
SETTINGSMEASURED SEPARATELY
Claude Opus 4.6 settings compared
SETTINGINTELLIGENCEA$ / 1MSPEED
Adaptive reasoning, max effort31.9A$14.04
Non-reasoning, high effort26.4A$14.04
§ 04 — AUSTRALIA

Running Claude Opus 4.6 in Australia.

It can run with requests kept in Australia on AWS Bedrock in Sydney and Melbourne. How the platforms compare →

AUSTRALIAN CLOUD REGIONS
Claude Opus 4.6 availability in Australian cloud regions
PLATFORMAVAILABILITYDETAIL
AWS Bedrock · SydneyAU ROUTING

Provider docs, checked 23 Sep 2026

AWS Bedrock · MelbourneAU ROUTING

Provider docs, checked 23 Sep 2026

Azure · Australia EastNOT IN AU

Provider docs, checked 23 Sep 2026

Google Vertex AI · SydneyGLOBAL

Provider docs, checked 23 Sep 2026

§ 06 — QUESTIONS

Claude Opus 4.6, answered.

Claude Opus 4.6 lists at US$5.00 per million input tokens and US$25.00 per million output tokens — A$7.02 and A$35.10 at A$1 = US$0.7123 (RBA, 22 Sep 2026), excluding GST. A typical customer support reply works out at about A$24.57 per 1,000 replies, before any reasoning tokens.

Claude Opus 4.6 can run with requests kept in Australia on AWS Bedrock in Sydney and Melbourne. Availability comes from the cloud providers’ own documentation; check your provider’s current terms before relying on it for data-residency obligations.

Anthropic documents a context window of 1,000,000 tokens (1M), with up to 128,000 output tokens. On AA-LCR, which tests reasoning across ~100,000-token document sets, it scores 78.0%.

PUT THE COMPARISON TO WORK

Need help choosing and using AI for your business?