Compare / Qwen3.7-Plus vs Qwen3.8-Max (0902)

Qwen3.7-Plus vs Qwen3.8-Max (0902)

Which is cheaper, which is more capable, and which does better at each kind of work, from 22 results on 2 sources that measured both models.

AlibabaQwen3.7-Plus Released 2 Jun 2026 · $0.32 in · $1.28 out
AlibabaQwen3.8-Max (0902) Released 3 Aug 2026 · $2.00 in · $6.00 out
Qwen3.7-Plus wins 21 too close to callQwen3.8-Max (0902) wins 19

Of the 22 results both models have, the better value on each. Results whose reported ranges overlap are too close to call.

Results as of 16 November 2026 (catalogue release 2026-11-16-49bdfa045dee).

Qwen3.7-Plus 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 25.2). Pick Qwen3.7-Plus if cost matters more: it costs 5.4 times less per token. Qwen3.7-Plus is also faster.

  • Qwen3.7-Plus is cheaper: $0.56 against $3.00 per million tokens, 5.4 times less.
  • Qwen3.8-Max (0902) scores higher on the Artificial Analysis Intelligence Index: 45.4 against 25.2.
  • Qwen3.7-Plus writes faster: 56 tokens a second against 37.
  • Qwen3.8-Max (0902) is newer: released 3 Aug 2026, against 2 Jun 2026 for Qwen3.7-Plus.
  • 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

25.2
Intelligence Index
45.4
$0.56
Price per million tokens, blendedlower is better
$3.00
56
Output speed, tokens a second
37
1,000,000
Context window, tokens
1,000,000

Every fact side by side

Qwen3.7-PlusQwen3.8-Max (0902)
Price per million tokens$0.32 in · $1.28 out$2.00 in · $6.00 out
Blended (3 in : 1 out)$0.56$3.00
Cheapest host, blended$0.56 (Alibaba)$3.00 (Alibaba)
Intelligence Index25.245.4
Spring Prompt overall–45
Output speed, tokens a second5637
Context window1,000,000 tokens1,000,000 tokens
Released2 Jun 20263 Aug 2026 (newer)
WeightsClosedClosed
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 26 of 32
Decks from an analysisTurning a finished analysis into a deck you could present as it is not measured 21 of 32
Marketing planningPlanning a year of ad spend without overspending not measured 27 of 32
Agents and tool useMulti-step tasks with tools: support desks, coding agents, function calls 77 of 159 10 of 159
Professional workReal tasks from banking, consulting and law, business documents and freelance projects not measured 18 of 51
Reasoning and knowledgeHard questions across science, maths and general knowledge 64 of 187 21 of 187
WritingWhat people prefer in blind comparisons, and judged writing quality 48 of 169 17 of 169
Sticking to the factsSummarising without inventing things, and factual answers 52 of 139 36 of 139
Speed under pressureGood decisions against a real clock (fast chess) not measured 36 of 36

From our research

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.

MeasureQwen3.7-PlusQwen3.8-Max (0902)
Arena (formerly LMArena) reported by Arena (formerly LMArena) · 3 results
Overall · TextArena rating, higher is better 59 · 20 of 387 measured 1,456 1,482
Overall · Text factualityArena rating, higher is better 52 · 22 of 163 measured 1,453 1,472
Business, management and finance · TextArena rating, higher is better 77 · 16 of 380 measured 1,445 1,484
Artificial Analysis reported by Artificial Analysis · 3 results
Artificial Analysis Intelligence Indexindex score, higher is better 79 · 15 of 249 measured 25.2 45.4
GPQA Diamond% of questions, higher is better 42 · 15 of 232 measured 90.0% 92.8%
Humanity's Last Exam% of questions, higher is better 63 · 30 of 250 measured 35.6% 43.1%
Show all 22 results (16 more)
MeasureQwen3.7-PlusQwen3.8-Max (0902)
Arena (formerly LMArena) reported by Arena (formerly LMArena) · 8 results
Confirmed task success · AgentIPS effect estimate, higher is better 40 · 20 of 48 measured -0.09arena agent 0.05arena agent
Creative writing · TextArena rating, higher is better 60 · 17 of 385 measured 1,432 1,468
Expert prompts · TextArena rating, higher is better 56 · 20 of 338 measured 1,485 1,513
Instruction following · TextArena rating, higher is better 58 · 25 of 387 measured 1,447 1,474
Praise over complaint · AgentIPS effect estimate, higher is better 40 · 20 of 48 measured -0.11arena agent 0.03arena agent
Steerability · AgentIPS effect estimate, higher is better 45 · 18 of 48 measured -0.08arena agent 0.03arena agent
Tool grounding · AgentIPS effect estimate, higher is better 42 · 43 of 48 measured -0.01arena agent -0.01arena agent
Writing, literature and language · TextArena rating, higher is better 61 · 18 of 386 measured 1,437 1,472
Artificial Analysis reported by Artificial Analysis · 8 results
Terminal-Bench 2.1% of tasks, higher is better 49 · 5 of 131 measured 61.0% 88.8%
Terminal-Bench 4.0% of tasks, higher is better 59 · 15 of 120 measured 1.0% 38.9%
τ-bench banking% of tasks, higher is better 52 · 7 of 121 measured 17.5% 47.8%
Artificial Analysis Coding Indexindex score, higher is better 48 · 10 of 130 measured 55.9 76.2
Long-context reasoning (AA-LCR)% of questions, higher is better 100 · 39 of 241 measured 73.0% 80.3%
Output speedtokens per second, higher is better 63 · 75 of 78 measured 56.1 36.8
SciCode% of problems, higher is better 70 · 42 of 121 measured 46.1% 52.1%
Time to first answer tokenseconds, lower is better 69 · 77 of 78 measured 37.3 56.2

Quick answers

Is Qwen3.7-Plus better than Qwen3.8-Max (0902)?

Pick Qwen3.8-Max (0902) if quality matters most: it scores higher (Intelligence Index 45.4 against 25.2). Pick Qwen3.7-Plus if cost matters more: it costs 5.4 times less per token. Qwen3.7-Plus is also faster.

Which is cheaper, Qwen3.7-Plus or Qwen3.8-Max (0902)?

Qwen3.7-Plus is cheaper: $0.56 against $3.00 per million tokens, 5.4 times less.

Which is faster, Qwen3.7-Plus or Qwen3.8-Max (0902)?

Qwen3.7-Plus writes about 56 tokens a second on its usual API, against 37 for Qwen3.8-Max (0902) (Artificial Analysis).

Which is better for agents and tool use, Qwen3.7-Plus or Qwen3.8-Max (0902)?

Qwen3.8-Max (0902) ranks 10 of 159 models on sale for multi-step tasks with tools: support desks, coding agents, function calls, against 77 for Qwen3.7-Plus.

Which is better for reasoning and knowledge, Qwen3.7-Plus or Qwen3.8-Max (0902)?

Qwen3.8-Max (0902) ranks 21 of 187 models on sale for hard questions across science, maths and general knowledge, against 64 for Qwen3.7-Plus.

Which is better for writing, Qwen3.7-Plus or Qwen3.8-Max (0902)?

Qwen3.8-Max (0902) ranks 17 of 169 models on sale for what people prefer in blind comparisons, and judged writing quality, against 48 for Qwen3.7-Plus.

Which is better for sticking to the facts, Qwen3.7-Plus or Qwen3.8-Max (0902)?

Qwen3.8-Max (0902) ranks 36 of 139 models on sale for summarising without inventing things, and factual answers, against 52 for Qwen3.7-Plus.

Run Qwen3.7-Plus and Qwen3.8-Max (0902) on your own prompt.

Benchmarks aren't your task. Test both side by side on your prompt, with every answer checked against your rules and the cost of each one.