Qwen3.8 Max benchmarks

Qwen3.8 Max is a proprietary model from Alibaba, released 3 Aug 2026. It ranks 16th of 51 on our overall leaderboard and 4th of 42 for coding. At A$4.21 per million tokens (blended), it costs 1.2× the median model we track. It writes about 42 tokens a second, and answers start after 50 s on average, thinking included. None of the major cloud platforms offer it in an Australian region yet.

#16 OF 51 OVERALLA$4.21 / 1M TOKENS1M CONTEXTUPDATED 23 SEP 2026
CONTEXT WINDOW
1,000,000 tokens
MAX OUTPUT
131,072 tokens
INPUT
text, image, video
WEIGHTS
Proprietary
RELEASED
3 Aug 2026
OUTPUT SPEED
42 tok/s
ANSWER STARTS AFTER
50 s (thinking included)
ALIBABA DOCS
§ 02 — RESULTS

Benchmark results.

Independent test scores are for the 0902 setting. “Among tracked” ranks Qwen3.8 Max against the 51 models on this site; LMArena ranks run across its full leaderboard.

ALL RESULTS8 OF 8 CORE SIGNALS
Qwen3.8 Max benchmark results
BENCHMARKRESULTAMONG TRACKEDSOURCE DETAIL
INDEPENDENT TESTS · ARTIFICIAL ANALYSIS
AA Intelligence Index45.4#11 of 510902
AA Coding Index76.2#9 of 420902
GPQA Diamond92.8%#14 of 440902
Humanity’s Last Exam43.1%#20 of 510902
AA-LCR80.3%#24 of 510902
Terminal-Bench 2.188.8%#3 of 420902
τ²-Bench (banking)47.8%#5 of 410902
SciCode52.1%#29 of 460902
BLIND HUMAN VOTES · LMARENA
LMArena Text16,670 votes · ±61481#19 of 42#22 of 402 on LMArena · 13 Sep 2026
LMArena WebDev3,221 votes · ±131671#4 of 45#4 of 129 on LMArena · 22 Sep 2026
LMArena Vision8,665 votes · ±81302#2 of 33#2 of 152 on LMArena · 13 Sep 2026
LMArena Agent31,489 sessions#17#15 of 37#17 of 46 on LMArena · 15 Sep 2026
§ 03 — COST

What Qwen3.8 Max 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
Qwen3.8 Max 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 Qwen3.8 Max in Australia.

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

AUSTRALIAN CLOUD REGIONS
Qwen3.8 Max 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

Qwen3.8 Max, answered.

Qwen3.8 Max 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 4th of 42 on our coding ranking, with an Artificial Analysis Coding Index of 76.2 and an LMArena WebDev rating of 1671 (4th of 129). The current leader is Claude Fable 5.1.

It ranks 7th of 41 on our agents ranking, completing 47.8% of τ²-Bench banking customer-service tasks and 88.8% of Terminal-Bench 2.1 tasks.

Artificial Analysis measures Qwen3.8 Max at about 42 tok/s of output, with the answer starting after 50 s on average once thinking time is included (0902 setting).

Alibaba documents a context window of 1,000,000 tokens (1M), with up to 131,072 output tokens. 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?