Enter opens the highlighted result. Esc closes.

Qwen3 32B vs Qwen3.5-122B-A10B

Qwen3.5-122B-A10B leads Qwen3 32B on the Artificial Analysis Intelligence Index, 17.7 to 7.3, and Qwen3 32B costs 5.2x less per output token ($0.40 vs $2.08 per million). Updated October 22, 2026; 33 benchmarks have a result for both.

Replace Qwen3 32B Replace Qwen3.5-122B-A10B
Qwen3 32BQwen
Coding
No data
Overall
40.8
Output $/M
$0.40
0
Qwen3.5-122B-A10BQwen
Coding
No data
Overall
No data
Output $/M
$2.08
33
vs boards won of 33 shared

Qwen3 32B or Qwen3.5-122B-A10B: which to pick

Neither model has a coding score yet, so the two cannot be ranked on coding.

Pick Qwen3 32B for output tokens 5.2x cheaper ($0.40 vs $2.08 per million) and work measured by SciCode or Terminal-Bench Hard (Artificial Analysis run), where it leads.

Model AQwen3 32BQwenNot benchmarkedNo coding benchmarkNo cost per solved taskModel BQwen3.5-122B-A10BQwenNot benchmarked1 independent benchmarkNo cost per solved task
Shared results
33
Qwen3 32B only
12
Qwen3.5-122B-A10B only
18
Like-for-like categories
7 of 9

Only benchmarks that tested both models count toward a pick; a result only one model has is shown but not compared.

Which one for your work

Each card is decided by one number both models carry. Where only one has it, the card says so and makes no call.

At a glance

Coding index
Qwen3 32B not benchmarked, Qwen3.5-122B-A10B not benchmarked.
Widest category
Agentic work, 63.7 points apart on average over 1 shared benchmark.
Widest single gap
Long context reasoning (AA-LCR): Qwen3 32B 0.0% against Qwen3.5-122B-A10B 76.3%, 76.3 points apart on a 0 to 100 scale.
Output price
Qwen3 32B $0.40 against Qwen3.5-122B-A10B $2.08 per million output tokens, 5.2x apart.
Context window
Qwen3 32B takes 131K tokens, Qwen3.5-122B-A10B 262K.

Benchmark by benchmark

First the score: boards each model leads, per category, where both have a result. Then every board, a category to a fold; bars are each result on a 0 to 100 scale, so compare the two in a row, not one row with another.

Boards won, where both have a result
CategoryQwen3 32BBarsQwen3.5-122B-A10BTies
Coding04
Intelligence01
Agentic work01
Reasoning05
Math02
Knowledge04
General016
All shared boards033
CodingLike-for-likeSix of these boards feed the Vibe Coding Index04
Coding benchmarks for Qwen3 32B and Qwen3.5-122B-A10B
BenchmarkQwen3 32BQwen3.5-122B-A10BLeader
Aider polyglot40.0%Not measuredOnly Qwen3 32B measured
LMArena WebDevNot measured1361Only Qwen3.5-122B-A10B measured
AA Coding IndexNot measured43.3Only Qwen3.5-122B-A10B measured
LiveCodeBench (Artificial Analysis run)54.6%Not measuredOnly Qwen3 32B measured
SciCode36.0%39.7%Qwen3.5-122B-A10B
Terminal-Bench Hard (Artificial Analysis run)3.0%31.1%Qwen3.5-122B-A10B
LMArena Text: coding13571436Qwen3.5-122B-A10B
LMArena Text: software and IT13661436Qwen3.5-122B-A10B
LMArena WebDev: ReactNot measured1353Only Qwen3.5-122B-A10B measured
LMArena WebDev: HTMLNot measured1351Only Qwen3.5-122B-A10B measured
Neither model has a result on the other 33 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index01
Intelligence benchmarks for Qwen3 32B and Qwen3.5-122B-A10B
BenchmarkQwen3 32BQwen3.5-122B-A10BLeader
AA Intelligence Index7.317.7Qwen3.5-122B-A10B
Epoch Capabilities Index138.4Not measuredOnly Qwen3 32B measured
Agentic workLike-for-likePublic boards, shown as published, kept out of the index01
Agentic work benchmarks for Qwen3 32B and Qwen3.5-122B-A10B
BenchmarkQwen3 32BQwen3.5-122B-A10BLeader
τ²-Bench Telecom29.8%93.6%Qwen3.5-122B-A10B
Berkeley Function Calling Leaderboard (BFCL)48.7%Not measuredOnly Qwen3 32B measured
BrowseComp-Plus10.7%Not measuredOnly Qwen3 32B measured
Neither model has a result on the other 39 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index05
Reasoning benchmarks for Qwen3 32B and Qwen3.5-122B-A10B
BenchmarkQwen3 32BQwen3.5-122B-A10BLeader
GPQA Diamond (Artificial Analysis run)66.8%85.7%Qwen3.5-122B-A10B
Humanity's Last Exam (Artificial Analysis run)7.4%25.2%Qwen3.5-122B-A10B
GPQA Diamond (Epoch AI run)65.7%Not measuredOnly Qwen3 32B measured
Mystery game puzzlesNot measured17.0%Only Qwen3.5-122B-A10B measured
LMArena Text: hard prompts13341421Qwen3.5-122B-A10B
LMArena Text: expert13621431Qwen3.5-122B-A10B
LMArena Text: hard prompts in English13501431Qwen3.5-122B-A10B
LMArena Vision: diagramsNot measured1249Only Qwen3.5-122B-A10B measured
LMArena Vision: homeworkNot measured1261Only Qwen3.5-122B-A10B measured
Kagi LLM Benchmark48.7%Not measuredOnly Qwen3 32B measured
Neither model has a result on the other 13 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index02
Math benchmarks for Qwen3 32B and Qwen3.5-122B-A10B
BenchmarkQwen3 32BQwen3.5-122B-A10BLeader
AA Math Index73.0Not measuredOnly Qwen3 32B measured
AIME 2025 (Artificial Analysis run)73.0%Not measuredOnly Qwen3 32B measured
OTIS Mock AIME66.9%Not measuredOnly Qwen3 32B measured
LMArena Text: math13991431Qwen3.5-122B-A10B
LMArena Text: mathematical work14201431Qwen3.5-122B-A10B
Neither model has a result on the other 9 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index04
Knowledge benchmarks for Qwen3 32B and Qwen3.5-122B-A10B
BenchmarkQwen3 32BQwen3.5-122B-A10BLeader
MMLU Pro (Artificial Analysis run)79.8%Not measuredOnly Qwen3 32B measured
LMArena Text: science13721432Qwen3.5-122B-A10B
LMArena Text: medicine and healthcare13681423Qwen3.5-122B-A10B
LMArena Text: legal and government13241422Qwen3.5-122B-A10B
LMArena Text: business and finance13181414Qwen3.5-122B-A10B
Neither model has a result on the other 15 boards here
Web designNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Web design benchmarks for Qwen3 32B and Qwen3.5-122B-A10B
BenchmarkQwen3 32BQwen3.5-122B-A10BLeader
Neither model has a result on 9 boards here
GeneralLike-for-likePublic boards, shown as published, kept out of the index016
General benchmarks for Qwen3 32B and Qwen3.5-122B-A10B
BenchmarkQwen3 32BQwen3.5-122B-A10BLeader
IFBench36.3%75.7%Qwen3.5-122B-A10B
Long context reasoning (AA-LCR)0.0%76.3%Qwen3.5-122B-A10B
DTBench67.5%84.3%Qwen3.5-122B-A10B
LMCA17.3%32.2%Qwen3.5-122B-A10B
Fiction.LiveBench74.2%Not measuredOnly Qwen3 32B measured
LMArena Text13401417Qwen3.5-122B-A10B
LMArena Text: instruction following13051399Qwen3.5-122B-A10B
LMArena Text: creative writing12971368Qwen3.5-122B-A10B
LMArena VisionNot measured1244Only Qwen3.5-122B-A10B measured
LMArena Text: English13591428Qwen3.5-122B-A10B
LMArena Text: non-English13171401Qwen3.5-122B-A10B
LMArena Text: Chinese13571463Qwen3.5-122B-A10B
LMArena Text: German13411425Qwen3.5-122B-A10B
LMArena Text: JapaneseNot measured1367Only Qwen3.5-122B-A10B measured
LMArena Text: KoreanNot measured1353Only Qwen3.5-122B-A10B measured
LMArena Text: FrenchNot measured1443Only Qwen3.5-122B-A10B measured
LMArena Text: SpanishNot measured1425Only Qwen3.5-122B-A10B measured
LMArena Text: Russian13111400Qwen3.5-122B-A10B
LMArena Text: PolishNot measured1398Only Qwen3.5-122B-A10B measured
LMArena Text: multi-turn13311416Qwen3.5-122B-A10B
LMArena Text: longer queries13271410Qwen3.5-122B-A10B
LMArena Text: writing and language12981387Qwen3.5-122B-A10B
LMArena Text: entertainment and media12791366Qwen3.5-122B-A10B
LMArena Vision: EnglishNot measured1249Only Qwen3.5-122B-A10B measured
LMArena Vision: ChineseNot measured1301Only Qwen3.5-122B-A10B measured
LMArena Vision: reading textNot measured1251Only Qwen3.5-122B-A10B measured
LMArena Vision: humorNot measured1243Only Qwen3.5-122B-A10B measured
LMArena Vision: creative writingNot measured1220Only Qwen3.5-122B-A10B measured
Neither model has a result on the other 20 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for Qwen3 32B and Qwen3.5-122B-A10B
BenchmarkQwen3 32BQwen3.5-122B-A10BLeader
Neither model has a result on 5 boards here

What each workload costs

Three fixed token mixes at each model's listed price, so per-token rates become a bill.

Chat turn

1K input + 500 output tokens

Qwen3 32B$0.0003Fits in one request
Qwen3.5-122B-A10B$0.0013Fits in one request

Qwen3 32B costs less

Repository review

50K input + 3K output tokens

Qwen3 32B$0.0082Fits in one request
Qwen3.5-122B-A10B$0.019Fits in one request

Qwen3 32B costs less

Agent loop

200K input + 10K output tokens

Qwen3 32B$0.032Exceeds the context window
Qwen3.5-122B-A10B$0.073Fits in one request

Qwen3 32B costs less

Listed OpenRouter rates, without cache or batch discounts. A workload that does not fit a model's context window would need splitting.

Specification differences

The leading value in a row is marked; a row with a missing value names no leader. Our two rows are marked in red.

Specifications of Qwen3 32B and Qwen3.5-122B-A10B
SpecificationQwen3 32BQwen3.5-122B-A10B
MakerQwenQwen
WeightsOpen weightsOpen weights
ReleasedApril 28, 2025February 25, 2026
Context window131K262K
Input $/Mtok$0.14$0.26
Output $/Mtok$0.40$2.08
Coding indexNot benchmarkedNot benchmarked
Independent measurements behind it01
Cost per solved taskNot computableNot computable
SourceOpenRouter listingOpenRouter listing

Questions

Is Qwen3 32B better than Qwen3.5-122B-A10B for coding?

Neither model has a coding score yet, so the two cannot be ranked on coding. Pick Qwen3 32B for output tokens 5.2x cheaper ($0.40 vs $2.08 per million) and work measured by SciCode or Terminal-Bench Hard (Artificial Analysis run), where it leads.

Which is cheaper, Qwen3 32B or Qwen3.5-122B-A10B?

Qwen3 32B costs $0.14 per million input tokens and $0.40 per million output tokens; Qwen3.5-122B-A10B costs $0.26 and $2.08. Cost per solved task is known for neither of them.

Which has the bigger context window, Qwen3 32B or Qwen3.5-122B-A10B?

Qwen3.5-122B-A10B, with 262K tokens against 131K.

How many benchmarks is the Qwen3 32B vs Qwen3.5-122B-A10B comparison based on?

33 benchmarks have a result for both models as of October 22, 2026. Qwen3 32B's coding index rests on 0 independent benchmarks and Qwen3.5-122B-A10B's on 1. Where only one model has a result, the page says so instead of naming a winner.

Compare next