GPT-6 Luna benchmarks

GPT-6 Luna is a proprietary model from OpenAI, released 22 Sep 2026. It ranks 45th of 54 on our overall leaderboard and 4th of 53 for value. At A$0.29 per million tokens (blended), it costs about 15× cheaper than the median model we track. It writes about 140 tokens a second, and answers start after 1.4 min on average, thinking included. It can be called from Microsoft Azure in Australia East, but only through global routing, so requests may be processed outside Australia.

#45 OF 54 OVERALLA$0.29 / 1M TOKENS1.05M CONTEXTUPDATED 2 OCT 2026
CONTEXT WINDOW
1,050,000 tokens
MAX OUTPUT
128,000 tokens
INPUT
text, image
WEIGHTS
Proprietary
RELEASED
22 Sep 2026
OUTPUT SPEED
140 tok/s
ANSWER STARTS AFTER
1.4 min (thinking included)
OPENAI DOCS ↗
§ 02 — RESULTS

Benchmark results.

Independent test scores are for the max effort setting. “Among tracked” ranks GPT-6 Luna against the 54 models on this site; LMArena ranks run across its full leaderboard.

ALL RESULTS6 OF 8 CORE SIGNALS
GPT-6 Luna benchmark results
BENCHMARKRESULTAMONG TRACKEDSOURCE DETAIL
INDEPENDENT TESTS · ARTIFICIAL ANALYSIS
AA Intelligence Index38.1#32 of 54max effort
Humanity’s Last Exam38.5%#44 of 54max effort
AA-LCR83.3%#11 of 54max effort
SciCode54.6%#25 of 49max effort
BLIND HUMAN VOTES · LMARENA
LMArena Text7,654 votes · ±71444#45 of 49#85 of 410 on LMArena · 30 Sep 2026
LMArena WebDev5,577 votes · ±91582#26 of 52#30 of 137 on LMArena · 30 Sep 2026
LMArena Agent12,076 sessions#22#21 of 42#22 of 46 on LMArena · 30 Sep 2026
§ 03 — COST

What GPT-6 Luna 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
GPT-6 Luna price per million tokens
PER MILLION TOKENSAUDUSD LIST
Input tokensA$0.14US$0.10
Output tokensA$0.72US$0.50
Blended (3 in : 1 out)A$0.29US$0.20
EVERYDAY JOBSESTIMATES
Estimated cost of common jobs in Australian dollars
JOBCOST (AUD)MEDIAN MODEL
Customer support replyPER 1,000 REPLIESA$0.50≈ A$8.20
Summarise a 30-page documentPER 100 DOCUMENTSA$0.35≈ A$5.35
Agentic coding taskPER 10 TASKSA$0.27≈ A$4.27
SETTINGSMEASURED SEPARATELY
GPT-6 Luna settings compared
SETTINGINTELLIGENCEA$ / 1MSPEED
max effort38.1A$0.29140 tok/s
xhigh effort34.6A$0.29124 tok/s
high effort32.9A$0.29131 tok/s
medium effort29.9A$0.29
low effort21.5A$0.29126 tok/s
Non-reasoning18.5A$0.29134 tok/s
§ 04 — AUSTRALIA

Running GPT-6 Luna in Australia.

It can be called from Microsoft Azure in Australia East, but only through global routing, so requests may be processed outside Australia. How the platforms compare →

AUSTRALIAN CLOUD REGIONS
GPT-6 Luna availability in Australian cloud regions
PLATFORMAVAILABILITYDETAIL
AWS Bedrock · SydneyNOT OFFERED
AWS Bedrock · MelbourneNOT OFFERED
Azure · Australia EastGLOBAL

Provider docs, checked 23 Sep 2026

Google Vertex AI · SydneyNOT OFFERED
§ 06 — QUESTIONS

GPT-6 Luna, answered.

GPT-6 Luna lists at US$0.10 per million input tokens and US$0.50 per million output tokens — A$0.14 and A$0.72 at A$1 = US$0.6949 (RBA, 1 Oct 2026), excluding GST. A typical customer support reply works out at about A$0.50 per 1,000 replies, before any reasoning tokens.

GPT-6 Luna can be called from Microsoft Azure in Australia East, 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.

Artificial Analysis measures GPT-6 Luna at about 140 tok/s of output, with the answer starting after 1.4 min on average once thinking time is included (max effort setting).

OpenAI documents a context window of 1,050,000 tokens (1.05M), with up to 128,000 output tokens. On AA-LCR, which tests reasoning across ~100,000-token document sets, it scores 83.3%.

PUT THE COMPARISON TO WORK

Need help choosing and using AI for your business?