Compare / Qwen3.5 397B A17B vs Hy3 preview

Qwen3.5 397B A17B vs Hy3 preview

Which is cheaper, which is more capable, and which does better at each kind of work, from 17 results on 3 sources that measured both models.

Qwen3.5 397B A17B
Alibaba · profile
Hy3 preview
Tencent · profile
Results compared
17
Shared sources
3

Qwen3.5 397B A17B or Hy3 preview? The short answer

  • Hy3 preview is cheaper: $0.29 against $1.29 per million tokens, 4.5 times less.
  • Hy3 preview scores higher on the Artificial Analysis Intelligence Index: 22.7 against 21.4.
  • On our business benchmarks, Qwen3.5 397B A17B ranks higher for reasoning and knowledge, writing and sticking to the facts.

At a glance

Qwen3.5 397B A17BHy3 preview
Price per million tokens$0.55 in · $3.50 out$0.18 in · $0.60 out
Blended (3 in : 1 out)$1.29$0.29
Cheapest host, blended$0.88 (Alibaba)–
Intelligence Index21.422.7
Spring Prompt overall––
Output speed, tokens a second90–
Context window262,144 tokens262,144 tokens
WeightsOpenOpen
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 models available today, for each kind of work, from our own benchmarks and licensed sources. The better rank is in green.

Use caseQwen3.5 397B A17BHy3 preview
Agents and tool useMulti-step tasks with tools: support desks, coding agents, function calls 65 of 161 not measured
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 69 of 195 73 of 195
WritingWhat people prefer in blind comparisons, and judged writing quality 66 of 187 86 of 187
Sticking to the factsSummarising without inventing things, and factual answers 72 of 153 128 of 153

Every shared result

BenchmarkMetricQwen3.5 397B A17BHy3 preview
Arena (formerly LMArena)reportedOverallArena rating 1,4451,413
Arena (formerly LMArena)reportedBusiness, management and financeArena rating 1,4451,411
Arena (formerly LMArena)reportedCreative writingArena rating 1,4051,354
Arena (formerly LMArena)reportedExpert promptsArena rating 1,4761,446
Arena (formerly LMArena)reportedInstruction followingArena rating 1,4341,397
Arena (formerly LMArena)reportedOverallArena rating 1,4421,409
Arena (formerly LMArena)reportedWriting, literature and languageArena rating 1,4211,378
Artificial AnalysisreportedArtificial Analysis Intelligence Indexindex score 21.422.7
Artificial AnalysisreportedGPQA Diamond% of questions 89.3%86.7%
Artificial AnalysisreportedHumanity's Last Exam% of questions 29.0%27.8%
Artificial AnalysisreportedIFBench% of instructions 78.8%63.1%
Artificial AnalysisreportedLong-context reasoning (AA-LCR)% of questions 77.3%64.7%
Artificial AnalysisreportedTerminal-Bench Hard% of tasks 40.9%34.1%
Artificial AnalysisreportedΤ²-bench telecom% of tasks 95.6%92.7%
UGI LeaderboardreportedRequested-length error% off the requested word count 23.0%18.0%
UGI LeaderboardreportedStyle adherencescore from 0 to 1 0.330.34
UGI LeaderboardreportedWriting scorescore out of 100 50.151.1

Bold green marks the better value on that metric. Where a source reports ranges that overlap, the difference may not be meaningful; see the benchmark page for ranges.

Quick answers

Is Qwen3.5 397B A17B better than Hy3 preview?

It depends on the task. Among models available today, on our benchmarks and licensed sources, Qwen3.5 397B A17B ranks higher for reasoning and knowledge, writing and sticking to the facts.

Which is cheaper, Qwen3.5 397B A17B or Hy3 preview?

Hy3 preview costs $0.29 per million tokens (three input to one output), against $1.29 for Qwen3.5 397B A17B.

Run Qwen3.5 397B A17B and Hy3 preview on your own prompt

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