Qwen3.8 Flash Next benchmarks

Qwen3.8 Flash Next is an open-weights model from Alibaba, released 26 Aug 2026. It ranks 25th of 51 on our overall leaderboard and 3rd of 50 for value, though some of its results are not yet published. At A$0.32 per million tokens (blended), it costs about 11× cheaper than the median model we track. It writes about 53 tokens a second, and answers start after 39 s on average, thinking included. Its weights are public, so it can be hosted in Australia on your own infrastructure or an Australian cloud region.

#25 OF 51 OVERALLA$0.32 / 1M TOKENS256K CONTEXTUPDATED 23 SEP 2026
CONTEXT WINDOW
262,144 tokens
INPUT
text, image, video
WEIGHTS
Open (qwen-community-1.0)
RELEASED
26 Aug 2026
OUTPUT SPEED
53 tok/s
ANSWER STARTS AFTER
39 s (thinking included)
ALIBABA DOCS
§ 02 — RESULTS

Benchmark results.

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

ALL RESULTS7 OF 8 CORE SIGNALS
Qwen3.8 Flash Next benchmark results
BENCHMARKRESULTAMONG TRACKEDSOURCE DETAIL
INDEPENDENT TESTS · ARTIFICIAL ANALYSIS
AA Intelligence Index39.8#21 of 51Default
AA Coding Index73.1#17 of 42Default
GPQA Diamond92.3%#19 of 44Default
Humanity’s Last Exam38.0%#42 of 51Default
AA-LCR79.7%#30 of 51Default
Terminal-Bench 2.186.1%#9 of 42Default
τ²-Bench (banking)45.4%#9 of 41Default
SciCode50.6%#36 of 46Default
BLIND HUMAN VOTES · LMARENA
LMArena WebDev4,313 votes · ±101636#7 of 45#9 of 129 on LMArena · 22 Sep 2026
LMArena Agent57,458 sessions#26#23 of 37#26 of 46 on LMArena · 15 Sep 2026
§ 03 — COST

What Qwen3.8 Flash Next 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 Flash Next price per million tokens
PER MILLION TOKENSAUDUSD LIST
Input tokensA$0.21US$0.15
Output tokensA$0.66US$0.47
Blended (3 in : 1 out)A$0.32US$0.23
EVERYDAY JOBSESTIMATES
Estimated cost of common jobs in Australian dollars
JOBCOST (AUD)MEDIAN MODEL
Customer support replyPER 1,000 REPLIESA$0.62A$6.58
Summarise a 30-page documentPER 100 DOCUMENTSA$0.47A$4.74
Agentic coding taskPER 10 TASKSA$0.37A$3.72
§ 04 — AUSTRALIA

Running Qwen3.8 Flash Next in Australia.

Its weights are public, so it can be hosted in Australia on your own infrastructure or an Australian cloud region. How the platforms compare →

AUSTRALIAN CLOUD REGIONS
Qwen3.8 Flash Next availability in Australian cloud regions
PLATFORMAVAILABILITYDETAIL
AWS Bedrock · SydneyNOT OFFERED
AWS Bedrock · MelbourneNOT OFFERED
Azure · Australia EastNOT OFFERED
Google Vertex AI · SydneyNOT OFFERED
Your own infrastructureSELF-HOST

Open weights: run it on your own servers or GPU instances in an Australian region.

§ 06 — QUESTIONS

Qwen3.8 Flash Next, answered.

Qwen3.8 Flash Next lists at US$0.15 per million input tokens and US$0.47 per million output tokens — A$0.21 and A$0.66 at A$1 = US$0.7123 (RBA, 22 Sep 2026), excluding GST. A typical customer support reply works out at about A$0.62 per 1,000 replies, before any reasoning tokens.

Qwen3.8 Flash Next’s weights are public, so it can be hosted in Australia on your own infrastructure or an Australian cloud region. Availability comes from the cloud providers’ own documentation; check your provider’s current terms before relying on it for data-residency obligations.

It ranks 13th of 42 on our coding ranking, with an Artificial Analysis Coding Index of 73.1 and an LMArena WebDev rating of 1636 (9th of 129). The current leader is Claude Fable 5.1.

It ranks 13th of 41 on our agents ranking, completing 45.4% of τ²-Bench banking customer-service tasks and 86.1% of Terminal-Bench 2.1 tasks.

Artificial Analysis measures Qwen3.8 Flash Next at about 53 tok/s of output, with the answer starting after 39 s on average once thinking time is included (default setting).

Alibaba documents a context window of 262,144 tokens (256K). On AA-LCR, which tests reasoning across ~100,000-token document sets, it scores 79.7%.

PUT THE COMPARISON TO WORK

Need help choosing and using AI for your business?