Compare / Qwen3.5-397B-A17B vs Inkling

Qwen3.5-397B-A17B vs Inkling

Which is cheaper, which is more capable, and which does better at each kind of work, from 19 results on 3 sources that measured both models.

AlibabaQwen3.5-397B-A17B Released 13 Feb 2026 · $0.55 in · $3.50 out
Thinking MachinesInkling Released 15 Jul 2026 · $0.95 in · $4.05 out
Qwen3.5-397B-A17B wins 45 too close to callInkling wins 10

Of the 19 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 Inkling? The short answer

Pick Inkling if quality matters most: it scores higher (Intelligence Index 25.0 against 21.4). Pick Qwen3.5-397B-A17B if cost matters more: it costs 25% less per token. Inkling is also faster.

  • Qwen3.5-397B-A17B is cheaper: $1.29 against $1.72 per million tokens, 25% less.
  • Inkling scores higher on the Artificial Analysis Intelligence Index: 25.0 against 21.4.
  • Inkling writes faster: 153 tokens a second against 90.
  • Inkling is newer: released 15 Jul 2026, against 13 Feb 2026 for Qwen3.5-397B-A17B.
  • On third-party benchmarks, on the results both models have: Inkling does better for agents and tool use, professional work, reasoning and knowledge and sticking to the facts.

Head to head

21.4
Intelligence Index
25.0
$1.29
Price per million tokens, blendedlower is better
$1.72
90
Output speed, tokens a second
153
262,144
Context window, tokens
524,288

Every fact side by side

Qwen3.5-397B-A17BInkling
Price per million tokens$0.55 in · $3.50 out$0.95 in · $4.05 out
Blended (3 in : 1 out)$1.29$1.72
Cheapest host, blended$0.88 (Alibaba)$1.72 (DeepInfra, FP8)
Intelligence Index21.425.0
Spring Prompt overall––
Output speed, tokens a second90153
Context window262,144 tokens524,288 tokens
Released13 Feb 202615 Jul 2026 (newer)
WeightsOpenOpen
Developer based inChinathe US

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 60 of 164
Professional workReal tasks from banking, consulting and law, business documents and freelance projects 48 of 51 45 of 51
Reasoning and knowledgeHard questions across science, maths and general knowledge 73 of 198 68 of 198
WritingWhat people prefer in blind comparisons, and judged writing quality 69 of 188 64 of 188
Sticking to the factsSummarising without inventing things, and factual answers 75 of 152 76 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-A17BInkling
APEX-Agents reported by APEX-Agents · 1 result
Tasks passed% of tasks, higher is better 36 · 34 of 37 measured 24.9% 33.8%
Arena (formerly LMArena) reported by Arena (formerly LMArena) · 3 results
Overall · TextArena rating, higher is better 80 · 83 of 387 measured 1,442 1,441
Overall · Text factualityArena rating, higher is better 70 · 58 of 163 measured 1,445 1,451
Business, management and finance · TextArena rating, higher is better 73 · 80 of 380 measured 1,446 1,444
Artificial Analysis reported by Artificial Analysis · 3 results
Artificial Analysis Intelligence Indexindex score, higher is better 97 · 76 of 243 measured 21.4no reasoning 25.0xhigh reasoning
GPQA Diamond% of questions, higher is better 53 · 65 of 231 measured 89.3% 87.2%xhigh reasoning
Humanity's Last Exam% of questions, higher is better 77 · 69 of 242 measured 29.0% 31.9%xhigh reasoning
Show all 19 results (12 more)
MeasureQwen3.5-397B-A17BInkling
Arena (formerly LMArena) reported by Arena (formerly LMArena) · 4 results
Creative writing · TextArena rating, higher is better 86 · 121 of 385 measured 1,405 1,379
Expert prompts · TextArena rating, higher is better 67 · 74 of 338 measured 1,477 1,473
Instruction following · TextArena rating, higher is better 78 · 87 of 387 measured 1,434 1,426
Writing, literature and language · TextArena rating, higher is better 80 · 109 of 386 measured 1,421 1,398
Artificial Analysis reported by Artificial Analysis · 8 results
Terminal-Bench 2.1% of tasks, higher is better 61 · 55 of 130 measured 51.3% 55.1%xhigh reasoning
Terminal-Bench 4.0% of tasks, higher is better 66 · 52 of 112 measured 0.0% 1.0%xhigh reasoning
τ-bench banking% of tasks, higher is better 64 · 37 of 121 measured 13.4% 29.1%xhigh reasoning
Artificial Analysis Coding Indexindex score, higher is better 61 · 55 of 131 measured 48.2 52.1xhigh reasoning
Long-context reasoning (AA-LCR)% of questions, higher is better 66 · 66 of 233 measured 77.3% 77.3%xhigh reasoning
Output speedtokens per second, higher is better 42 · 18 of 74 measured 90.0 153xhigh reasoning
SciCode% of problems, higher is better 66 · 58 of 113 measured 44.8% 47.0%xhigh reasoning
Time to first answer tokenseconds, lower is better 34 · 52 of 74 measured 1.59no reasoning 15.4xhigh reasoning

Quick answers

Is Qwen3.5-397B-A17B better than Inkling?

Pick Inkling if quality matters most: it scores higher (Intelligence Index 25.0 against 21.4). Pick Qwen3.5-397B-A17B if cost matters more: it costs 25% less per token. Inkling is also faster.

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

Qwen3.5-397B-A17B is cheaper: $1.29 against $1.72 per million tokens, 25% less.

Which is faster, Qwen3.5-397B-A17B or Inkling?

Inkling writes about 153 tokens a second on its usual API, against 90 for Qwen3.5-397B-A17B (Artificial Analysis).

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

Inkling ranks 60 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 Inkling?

Inkling ranks 45 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 Inkling?

Inkling ranks 68 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 Inkling?

Inkling ranks 64 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 Inkling?

Inkling: 524,288 tokens, against 262,144 for Qwen3.5-397B-A17B.

Run Qwen3.5-397B-A17B and Inkling 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