Compare / Qwen3.5-397B-A17B vs Qwen3.6-Plus

Qwen3.5-397B-A17B vs Qwen3.6-Plus

Which is cheaper, which is more capable, and which does better at each kind of work, from 20 results on 3 sources that measured both models.

AlibabaQwen3.5-397B-A17B Released 13 Feb 2026 · $0.55 in · $3.50 out
AlibabaQwen3.6-Plus Released 31 Mar 2026 · $0.33 in · $1.95 out
Qwen3.5-397B-A17B wins 46 too close to callQwen3.6-Plus wins 10

Of the 20 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 Qwen3.6-Plus? The short answer

Pick Qwen3.6-Plus: it scores higher (Intelligence Index 27.0 against 21.4) and costs less.

  • Qwen3.6-Plus is cheaper: $0.73 against $1.29 per million tokens, 43% less.
  • Qwen3.6-Plus scores higher on the Artificial Analysis Intelligence Index: 27.0 against 21.4.
  • Qwen3.6-Plus is newer: released 31 Mar 2026, against 13 Feb 2026 for Qwen3.5-397B-A17B.
  • On third-party benchmarks, on the results both models have: Qwen3.5-397B-A17B does better for reasoning and knowledge and sticking to the facts; Qwen3.6-Plus for agents and tool use and writing.

Head to head

21.4
Intelligence Index
27.0
$1.29
Price per million tokens, blendedlower is better
$0.73
262,144
Context window, tokens
1,000,000

Every fact side by side

Qwen3.5-397B-A17BQwen3.6-Plus
Price per million tokens$0.55 in · $3.50 out$0.33 in · $1.95 out
Blended (3 in : 1 out)$1.29$0.73
Cheapest host, blended$0.88 (Alibaba)–
Intelligence Index21.427.0
Spring Prompt overall––
Output speed, tokens a second90–
Context window262,144 tokens1,000,000 tokens
Released13 Feb 202631 Mar 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.

Agents and tool useMulti-step tasks with tools: support desks, coding agents, function calls 70 of 164 63 of 164
Professional workReal tasks from banking, consulting and law, business documents and freelance projects 48 of 51 not measured
Reasoning and knowledgeHard questions across science, maths and general knowledge 73 of 198 67 of 198
WritingWhat people prefer in blind comparisons, and judged writing quality 69 of 188 54 of 188
Sticking to the factsSummarising without inventing things, and factual answers 75 of 152 80 of 152

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-A17BQwen3.6-Plus
Arena (formerly LMArena) reported by Arena (formerly LMArena) · 3 results
Overall · TextArena rating, higher is better 80 · 76 of 387 measured 1,442 1,443
Overall · Text factualityArena rating, higher is better 70 · 84 of 163 measured 1,445 1,438
Business, management and finance · TextArena rating, higher is better 73 · 75 of 380 measured 1,446 1,446
Artificial Analysis reported by Artificial Analysis · 3 results
Artificial Analysis Intelligence Indexindex score, higher is better 97 · 62 of 243 measured 21.4no reasoning 27.0
GPQA Diamond% of questions, higher is better 53 · 58 of 231 measured 89.3% 88.2%
Humanity's Last Exam% of questions, higher is better 77 · 84 of 242 measured 29.0% 27.8%
UGI Leaderboard reported by UGI Leaderboard · 3 results
Writing score · UGIscore out of 100, higher is better 77 · 49 of 230 measured 50.1no reasoning 58.2thinking reasoning
Requested-length error · UGI% off the requested word count, lower is better 134 · 25 of 230 measured 23.0%no reasoning 8.0%thinking reasoning
Style adherence · UGIscore from 0 to 1, higher is better 164 · 96 of 230 measured 0.33no reasoning 0.35no reasoning
Show all 20 results (11 more)
MeasureQwen3.5-397B-A17BQwen3.6-Plus
Arena (formerly LMArena) reported by Arena (formerly LMArena) · 4 results
Creative writing · TextArena rating, higher is better 86 · 82 of 385 measured 1,405 1,407
Expert prompts · TextArena rating, higher is better 67 · 68 of 338 measured 1,477 1,476
Instruction following · TextArena rating, higher is better 78 · 74 of 387 measured 1,434 1,435
Writing, literature and language · TextArena rating, higher is better 80 · 76 of 386 measured 1,421 1,423
Artificial Analysis reported by Artificial Analysis · 7 results
Terminal-Bench 2.1% of tasks, higher is better 61 · 47 of 130 measured 51.3% 61.4%
τ-bench banking% of tasks, higher is better 64 · 48 of 121 measured 13.4% 20.8%
Artificial Analysis Coding Indexindex score, higher is better 61 · 50 of 131 measured 48.2 54.5
IFBench% of instructions, higher is better 8 · 29 of 195 measured 78.8% 75.2%
Long-context reasoning (AA-LCR)% of questions, higher is better 66 · 54 of 233 measured 77.3% 78.3%
Terminal-Bench Hard% of tasks, higher is better 34 · 23 of 190 measured 40.9% 43.9%
τ²-bench telecom% of tasks, higher is better 16 · 7 of 193 measured 95.6% 97.7%

Quick answers

Is Qwen3.5-397B-A17B better than Qwen3.6-Plus?

Pick Qwen3.6-Plus: it scores higher (Intelligence Index 27.0 against 21.4) and costs less.

Which is cheaper, Qwen3.5-397B-A17B or Qwen3.6-Plus?

Qwen3.6-Plus is cheaper: $0.73 against $1.29 per million tokens, 43% less.

Which is better for agents and tool use, Qwen3.5-397B-A17B or Qwen3.6-Plus?

Qwen3.6-Plus ranks 63 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 reasoning and knowledge, Qwen3.5-397B-A17B or Qwen3.6-Plus?

Qwen3.6-Plus ranks 67 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 Qwen3.6-Plus?

Qwen3.6-Plus ranks 54 of 188 models on sale for what people prefer in blind comparisons, and judged writing quality, against 69 for Qwen3.5-397B-A17B.

Which is better for sticking to the facts, Qwen3.5-397B-A17B or Qwen3.6-Plus?

Qwen3.5-397B-A17B ranks 75 of 152 models on sale for summarising without inventing things, and factual answers, against 80 for Qwen3.6-Plus.

Which has the bigger context window, Qwen3.5-397B-A17B or Qwen3.6-Plus?

Qwen3.6-Plus: 1,000,000 tokens, against 262,144 for Qwen3.5-397B-A17B.

Run Qwen3.5-397B-A17B and Qwen3.6-Plus 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