Compare / Qwen3.5-397B-A17B vs Qwen3.8-Max (0902)

Qwen3.5-397B-A17B vs Qwen3.8-Max (0902)

Which is cheaper, which is more capable, and which does better at each kind of work, from 18 results on 2 sources that measured both models.

AlibabaQwen3.5-397B-A17B Released 13 Feb 2026 · $0.55 in · $3.50 out
AlibabaQwen3.8-Max (0902) Released 3 Aug 2026 · $2.00 in · $6.00 out
Qwen3.5-397B-A17B wins 2Qwen3.8-Max (0902) wins 16

Of the 18 results both models have, the better value on each. Results whose reported ranges overlap are too close to call.

Results as of 9 October 2026 (catalogue release 2026-10-09-dd620e778ac5).

Qwen3.5-397B-A17B or Qwen3.8-Max (0902)? The short answer

Pick Qwen3.8-Max (0902) if quality matters most: it scores higher (Intelligence Index 45.4 against 21.4). Pick Qwen3.5-397B-A17B if cost matters more: it costs 2.3 times less per token. Qwen3.5-397B-A17B is also faster.

  • Qwen3.5-397B-A17B is cheaper: $1.29 against $3.00 per million tokens, 2.3 times less.
  • Qwen3.8-Max (0902) scores higher on the Artificial Analysis Intelligence Index: 45.4 against 21.4.
  • Qwen3.5-397B-A17B writes faster: 90 tokens a second against 37.
  • Qwen3.8-Max (0902) is newer: released 3 Aug 2026, against 13 Feb 2026 for Qwen3.5-397B-A17B.
  • On third-party benchmarks, on the results both models have: Qwen3.8-Max (0902) does better for agents and tool use, reasoning and knowledge, writing and sticking to the facts.

Head to head

21.4
Intelligence Index
45.4
$1.29
Price per million tokens, blendedlower is better
$3.00
90
Output speed, tokens a second
37
262,144
Context window, tokens
1,000,000

Every fact side by side

Qwen3.5-397B-A17BQwen3.8-Max (0902)
Price per million tokens$0.55 in · $3.50 out$2.00 in · $6.00 out
Blended (3 in : 1 out)$1.29$3.00
Cheapest host, blended$0.88 (Alibaba)–
Intelligence Index21.445.4
Spring Prompt overall–48
Output speed, tokens a second9037
Context window262,144 tokens1,000,000 tokens
Released13 Feb 20263 Aug 2026 (newer)
WeightsOpenClosed
Developer based inChinaChina

Prices are the developer's list price where we have read it, otherwise the typical host on OpenRouter; see every model's price. Intelligence and speed from Artificial Analysis.

Which is better for what

Each model's rank among the models on sale today, for each kind of work, from our own benchmarks and licensed sources. Further right is better; the better rank is in green.

Product listingsTurning a sparse product feed and photos into listings that can go live not measured 17 of 20
Decks from an analysisTurning a finished analysis into a deck you could present as it is not measured 11 of 19
Marketing planningPlanning a year of ad spend without overspending not measured 14 of 19
Agents and tool useMulti-step tasks with tools: support desks, coding agents, function calls 70 of 164 7 of 164
Professional workReal tasks from banking, consulting and law, business documents and freelance projects 48 of 51 18 of 51
Reasoning and knowledgeHard questions across science, maths and general knowledge 73 of 198 17 of 198
WritingWhat people prefer in blind comparisons, and judged writing quality 69 of 188 16 of 188
Sticking to the factsSummarising without inventing things, and factual answers 75 of 152 38 of 152
Speed under pressureGood decisions against a real clock (fast chess) not measured 24 of 24

Every shared result

Each model's best result on every measure both have, grouped by benchmark, with the setting that produced it. Under each measure, every model that benchmark has measured is a grey tick, best to the right, so you can see where the two sit in the field. The headline measures of each benchmark come first; the rest are under "Show all". Green marks the better value; where a source reports ranges that overlap, neither is marked.

MeasureQwen3.5-397B-A17BQwen3.8-Max (0902)
Arena (formerly LMArena) reported by Arena (formerly LMArena) · 3 results
Overall · TextArena rating, higher is better 80 · 20 of 387 measured 1,442 1,482
Overall · Text factualityArena rating, higher is better 70 · 22 of 163 measured 1,445 1,472
Business, management and finance · TextArena rating, higher is better 73 · 16 of 380 measured 1,446 1,484
Artificial Analysis reported by Artificial Analysis · 3 results
Artificial Analysis Intelligence Indexindex score, higher is better 97 · 14 of 243 measured 21.4no reasoning 45.4
GPQA Diamond% of questions, higher is better 53 · 15 of 231 measured 89.3% 92.8%
Humanity's Last Exam% of questions, higher is better 77 · 24 of 242 measured 29.0% 43.1%
Show all 18 results (12 more)
MeasureQwen3.5-397B-A17BQwen3.8-Max (0902)
Arena (formerly LMArena) reported by Arena (formerly LMArena) · 4 results
Creative writing · TextArena rating, higher is better 86 · 17 of 385 measured 1,405 1,468
Expert prompts · TextArena rating, higher is better 67 · 20 of 338 measured 1,477 1,513
Instruction following · TextArena rating, higher is better 78 · 25 of 387 measured 1,434 1,474
Writing, literature and language · TextArena rating, higher is better 80 · 18 of 386 measured 1,421 1,472
Artificial Analysis reported by Artificial Analysis · 8 results
Terminal-Bench 2.1% of tasks, higher is better 61 · 5 of 130 measured 51.3% 88.8%
Terminal-Bench 4.0% of tasks, higher is better 66 · 12 of 112 measured 0.0% 38.9%
τ-bench banking% of tasks, higher is better 64 · 7 of 121 measured 13.4% 47.8%
Artificial Analysis Coding Indexindex score, higher is better 61 · 10 of 131 measured 48.2 76.2
Long-context reasoning (AA-LCR)% of questions, higher is better 66 · 35 of 233 measured 77.3% 80.3%
Output speedtokens per second, higher is better 42 · 71 of 74 measured 90.0 37.0
SciCode% of problems, higher is better 66 · 36 of 113 measured 44.8% 52.1%
Time to first answer tokenseconds, lower is better 34 · 74 of 74 measured 1.59no reasoning 55.8

Quick answers

Is Qwen3.5-397B-A17B better than Qwen3.8-Max (0902)?

Pick Qwen3.8-Max (0902) if quality matters most: it scores higher (Intelligence Index 45.4 against 21.4). Pick Qwen3.5-397B-A17B if cost matters more: it costs 2.3 times less per token. Qwen3.5-397B-A17B is also faster.

Which is cheaper, Qwen3.5-397B-A17B or Qwen3.8-Max (0902)?

Qwen3.5-397B-A17B is cheaper: $1.29 against $3.00 per million tokens, 2.3 times less.

Which is faster, Qwen3.5-397B-A17B or Qwen3.8-Max (0902)?

Qwen3.5-397B-A17B writes about 90 tokens a second on its usual API, against 37 for Qwen3.8-Max (0902) (Artificial Analysis).

Which is better for agents and tool use, Qwen3.5-397B-A17B or Qwen3.8-Max (0902)?

Qwen3.8-Max (0902) ranks 7 of 164 models on sale for multi-step tasks with tools: support desks, coding agents, function calls, against 70 for Qwen3.5-397B-A17B.

Which is better for professional work, Qwen3.5-397B-A17B or Qwen3.8-Max (0902)?

Qwen3.8-Max (0902) ranks 18 of 51 models on sale for real tasks from banking, consulting and law, business documents and freelance projects, against 48 for Qwen3.5-397B-A17B.

Which is better for reasoning and knowledge, Qwen3.5-397B-A17B or Qwen3.8-Max (0902)?

Qwen3.8-Max (0902) ranks 17 of 198 models on sale for hard questions across science, maths and general knowledge, against 73 for Qwen3.5-397B-A17B.

Which is better for writing, Qwen3.5-397B-A17B or Qwen3.8-Max (0902)?

Qwen3.8-Max (0902) ranks 16 of 188 models on sale for what people prefer in blind comparisons, and judged writing quality, against 69 for Qwen3.5-397B-A17B.

Which has the bigger context window, Qwen3.5-397B-A17B or Qwen3.8-Max (0902)?

Qwen3.8-Max (0902): 1,000,000 tokens, against 262,144 for Qwen3.5-397B-A17B.

Run Qwen3.5-397B-A17B and Qwen3.8-Max (0902) on your own prompt

Benchmarks aren't your data. Try both side by side in the playground, with the cost of every answer.

Try the playgroundTalk to us