Compare / Qwen2.5-72B-Instruct vs Qwen3.8-Max (0902)

Qwen2.5-72B-Instruct vs Qwen3.8-Max (0902)

Which is cheaper, which is more capable, and which does better at each kind of work, from 9 results on 2 sources that measured both models.

AlibabaQwen2.5-72B-Instruct Released 17 Sep 2024 · $0.36 in · $0.40 out
AlibabaQwen3.8-Max (0902) Released 3 Aug 2026 · $2.00 in · $6.00 out
Qwen2.5-72B-Instruct wins 0Qwen3.8-Max (0902) wins 9

Of the 9 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).

Qwen2.5-72B-Instruct 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 7.7). Pick Qwen2.5-72B-Instruct if cost matters more: it costs 8.1 times less per token.

  • Qwen2.5-72B-Instruct is cheaper: $0.37 against $3.00 per million tokens, 8.1 times less.
  • Qwen3.8-Max (0902) scores higher on the Artificial Analysis Intelligence Index: 45.4 against 7.7.
  • Qwen3.8-Max (0902) is newer: released 3 Aug 2026, against 17 Sep 2024 for Qwen2.5-72B-Instruct.
  • On third-party benchmarks, on the results both models have: Qwen3.8-Max (0902) does better for reasoning and knowledge and writing.

Head to head

7.7
Intelligence Index
45.4
$0.37
Price per million tokens, blendedlower is better
$3.00
32,768
Context window, tokens
1,000,000

Every fact side by side

Qwen2.5-72B-InstructQwen3.8-Max (0902)
Price per million tokens$0.36 in · $0.40 out$2.00 in · $6.00 out
Blended (3 in : 1 out)$0.37$3.00
Cheapest host, blended–$3.00 (Alibaba)
Intelligence Index7.745.4
Spring Prompt overall–45
Output speed, tokens a second–37
Context window32,768 tokens1,000,000 tokens
Released17 Sep 20243 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 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 not measured 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 167 of 187 21 of 187
WritingWhat people prefer in blind comparisons, and judged writing quality 146 of 169 17 of 169
Sticking to the factsSummarising without inventing things, and factual answers not measured 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.

MeasureQwen2.5-72B-InstructQwen3.8-Max (0902)
Arena (formerly LMArena) reported by Arena (formerly LMArena) · 3 results
Overall · TextArena rating, higher is better 257 · 20 of 387 measured 1,303 1,482
Business, management and finance · TextArena rating, higher is better 245 · 16 of 380 measured 1,299 1,484
Creative writing · TextArena rating, higher is better 265 · 17 of 385 measured 1,254 1,468
Artificial Analysis reported by Artificial Analysis · 3 results
Artificial Analysis Intelligence Indexindex score, higher is better 205 · 15 of 249 measured 7.7 45.4
GPQA Diamond% of questions, higher is better 207 · 15 of 232 measured 49.1% 92.8%
Humanity's Last Exam% of questions, higher is better 237 · 30 of 250 measured 3.6% 43.1%
Show all 9 results (3 more)
MeasureQwen2.5-72B-InstructQwen3.8-Max (0902)
Arena (formerly LMArena) reported by Arena (formerly LMArena) · 3 results
Expert prompts · TextArena rating, higher is better 244 · 20 of 338 measured 1,295 1,513
Instruction following · TextArena rating, higher is better 245 · 25 of 387 measured 1,292 1,474
Writing, literature and language · TextArena rating, higher is better 253 · 18 of 386 measured 1,282 1,472

Quick answers

Is Qwen2.5-72B-Instruct better than Qwen3.8-Max (0902)?

Pick Qwen3.8-Max (0902) if quality matters most: it scores higher (Intelligence Index 45.4 against 7.7). Pick Qwen2.5-72B-Instruct if cost matters more: it costs 8.1 times less per token.

Which is cheaper, Qwen2.5-72B-Instruct or Qwen3.8-Max (0902)?

Qwen2.5-72B-Instruct is cheaper: $0.37 against $3.00 per million tokens, 8.1 times less.

Which is better for reasoning and knowledge, Qwen2.5-72B-Instruct 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 167 for Qwen2.5-72B-Instruct.

Which is better for writing, Qwen2.5-72B-Instruct 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 146 for Qwen2.5-72B-Instruct.

Which has the bigger context window, Qwen2.5-72B-Instruct or Qwen3.8-Max (0902)?

Qwen3.8-Max (0902): 1,000,000 tokens, against 32,768 for Qwen2.5-72B-Instruct.

Run Qwen2.5-72B-Instruct 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.