Enter opens the highlighted result. Esc closes.

Qwen3 235B A22B Thinking 2507 vs Qwen3.5 397B A17B

Qwen3.5 397B A17B leads Qwen3 235B A22B Thinking 2507 on the Artificial Analysis Intelligence Index, 21.4 to 12.7, and Qwen3.5 397B A17B costs 1.5x less per output token ($2.34 vs $3.50 per million). Updated October 22, 2026; 39 benchmarks have a result for both.

Replace Qwen3 235B A22B Thinking 2507 Replace Qwen3.5 397B A17B
Qwen3 235B A22B Thinking 2507Qwen
Coding
No data
Overall
52.9
Output $/M
$3.50
2
Qwen3.5 397B A17BQwen
Coding
No data
Overall
57.1
Output $/M
$2.34
37
vs boards won of 39 shared

Qwen3 235B A22B Thinking 2507 or Qwen3.5 397B A17B: which to pick

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

Pick Qwen3 235B A22B Thinking 2507 for work measured by LMArena Text: coding or LMArena Text: software and IT, where it leads.

Model AQwen3 235B A22B Thinking 2507QwenNot benchmarkedNo coding benchmarkNo cost per solved taskModel BQwen3.5 397B A17BQwenNot benchmarked1 independent benchmarkNo cost per solved task
Shared results
39
Qwen3 235B A22B Thinking 2507 only
7
Qwen3.5 397B A17B only
27
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 235B A22B Thinking 2507 not benchmarked, Qwen3.5 397B A17B not benchmarked.
Widest category
Web design, 22.4 points apart on average over 6 shared benchmarks.
Widest single gap
Design Arena: data viz: Qwen3 235B A22B Thinking 2507 950 against Qwen3.5 397B A17B 1175, 28.1 points apart on a 0 to 100 scale.
Output price
Qwen3 235B A22B Thinking 2507 $3.50 against Qwen3.5 397B A17B $2.34 per million output tokens, 1.5x apart.
Context window
Qwen3 235B A22B Thinking 2507 takes 128K tokens, Qwen3.5 397B A17B 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 235B A22B Thinking 2507BarsQwen3.5 397B A17BTies
Coding02
Intelligence01
Reasoning14
Math03
Knowledge13
Web design06
General018
All shared boards237
CodingLike-for-likeSix of these boards feed the Vibe Coding Index02
Coding benchmarks for Qwen3 235B A22B Thinking 2507 and Qwen3.5 397B A17B
BenchmarkQwen3 235B A22B Thinking 2507Qwen3.5 397B A17BLeader
LMArena WebDevNot measured1400Only Qwen3.5 397B A17B measured
AA Coding Index22.1Not measuredOnly Qwen3 235B A22B Thinking 2507 measured
SciCodeNot measured44.8%Only Qwen3.5 397B A17B measured
Terminal-Bench Hard (Artificial Analysis run)Not measured40.9%Only Qwen3.5 397B A17B measured
WeirdML41.0%Not measuredOnly Qwen3 235B A22B Thinking 2507 measured
ALE-BenchNot measured621.9Only Qwen3.5 397B A17B measured
LMArena Text: coding14241464Qwen3.5 397B A17B
LMArena Text: software and IT14311463Qwen3.5 397B A17B
LMArena WebDev: ReactNot measured1388Only Qwen3.5 397B A17B measured
LMArena WebDev: HTMLNot measured1410Only Qwen3.5 397B A17B 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 235B A22B Thinking 2507 and Qwen3.5 397B A17B
BenchmarkQwen3 235B A22B Thinking 2507Qwen3.5 397B A17BLeader
AA Intelligence Index12.721.4Qwen3.5 397B A17B
Epoch Capabilities IndexNot measured146.8Only Qwen3.5 397B A17B measured
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index4 boards, none shared
Agentic work benchmarks for Qwen3 235B A22B Thinking 2507 and Qwen3.5 397B A17B
BenchmarkQwen3 235B A22B Thinking 2507Qwen3.5 397B A17BLeader
AA Agentic Index1.3Not measuredOnly Qwen3 235B A22B Thinking 2507 measured
τ²-Bench TelecomNot measured95.6%Only Qwen3.5 397B A17B measured
APEX-AgentsNot measured24.9%Only Qwen3.5 397B A17B measured
Vending-Bench 2-$11Not measuredOnly Qwen3 235B A22B Thinking 2507 measured
Neither model has a result on the other 38 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index14
Reasoning benchmarks for Qwen3 235B A22B Thinking 2507 and Qwen3.5 397B A17B
BenchmarkQwen3 235B A22B Thinking 2507Qwen3.5 397B A17BLeader
GPQA Diamond (Artificial Analysis run)Not measured89.3%Only Qwen3.5 397B A17B measured
Humanity's Last Exam (Artificial Analysis run)Not measured29.0%Only Qwen3.5 397B A17B measured
GPQA Diamond (Epoch AI run)80.1%86.4%Qwen3.5 397B A17B
Mystery game puzzles9.0%18.0%Qwen3.5 397B A17B
LMArena Text: hard prompts14161448Qwen3.5 397B A17B
LMArena Text: expert14631462Qwen3 235B A22B Thinking 2507
LMArena Text: hard prompts in English14321450Qwen3.5 397B A17B
LMArena Vision: diagramsNot measured1277Only Qwen3.5 397B A17B measured
LMArena Vision: homeworkNot measured1292Only Qwen3.5 397B A17B measured
Neither model has a result on the other 14 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index03
Math benchmarks for Qwen3 235B A22B Thinking 2507 and Qwen3.5 397B A17B
BenchmarkQwen3 235B A22B Thinking 2507Qwen3.5 397B A17BLeader
OTIS Mock AIME86.7%88.9%Qwen3.5 397B A17B
FrontierMath, tiers 1 to 3Not measured31.2%Only Qwen3.5 397B A17B measured
LMArena Text: math14121453Qwen3.5 397B A17B
LMArena Text: mathematical work14351454Qwen3.5 397B A17B
MathArenaNot measured19.2%Only Qwen3.5 397B A17B measured
Neither model has a result on the other 9 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index13
Knowledge benchmarks for Qwen3 235B A22B Thinking 2507 and Qwen3.5 397B A17B
BenchmarkQwen3 235B A22B Thinking 2507Qwen3.5 397B A17BLeader
SimpleQA Verified40.4%Not measuredOnly Qwen3 235B A22B Thinking 2507 measured
LMArena Text: science14331457Qwen3.5 397B A17B
LMArena Text: medicine and healthcare14561455Qwen3 235B A22B Thinking 2507
LMArena Text: legal and government14151441Qwen3.5 397B A17B
LMArena Text: business and finance14131435Qwen3.5 397B A17B
Neither model has a result on the other 15 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index06
Web design benchmarks for Qwen3 235B A22B Thinking 2507 and Qwen3.5 397B A17B
BenchmarkQwen3 235B A22B Thinking 2507Qwen3.5 397B A17BLeader
Design Arena: websites10521190Qwen3.5 397B A17B
Design Arena: UI components9421161Qwen3.5 397B A17B
Design Arena: game dev9561140Qwen3.5 397B A17B
Design Arena: data viz9501175Qwen3.5 397B A17B
Design Arena: 3D9971160Qwen3.5 397B A17B
Design Arena: all code categories10321179Qwen3.5 397B A17B
Design Arena: SVGNot measured1139Only Qwen3.5 397B A17B measured
Neither model has a result on the other 2 boards here
GeneralLike-for-likePublic boards, shown as published, kept out of the index018
General benchmarks for Qwen3 235B A22B Thinking 2507 and Qwen3.5 397B A17B
BenchmarkQwen3 235B A22B Thinking 2507Qwen3.5 397B A17BLeader
IFBenchNot measured78.8%Only Qwen3.5 397B A17B measured
Long context reasoning (AA-LCR)Not measured77.3%Only Qwen3.5 397B A17B measured
DTBench80.3%87.5%Qwen3.5 397B A17B
LMCA29.3%37.9%Qwen3.5 397B A17B
Fiction.LiveBench75.0%Not measuredOnly Qwen3 235B A22B Thinking 2507 measured
Creative writing (Lech Mazur)82.4%Not measuredOnly Qwen3 235B A22B Thinking 2507 measured
LMArena Text14151437Qwen3.5 397B A17B
LMArena Text: instruction following13861424Qwen3.5 397B A17B
LMArena Text: creative writing13841402Qwen3.5 397B A17B
LMArena VisionNot measured1262Only Qwen3.5 397B A17B measured
LMArena Text: English14291443Qwen3.5 397B A17B
LMArena Text: non-English13971430Qwen3.5 397B A17B
LMArena Text: Chinese14811498Qwen3.5 397B A17B
LMArena Text: German14081445Qwen3.5 397B A17B
LMArena Text: Japanese13861429Qwen3.5 397B A17B
LMArena Text: Korean13751384Qwen3.5 397B A17B
LMArena Text: FrenchNot measured1462Only Qwen3.5 397B A17B measured
LMArena Text: Spanish13891441Qwen3.5 397B A17B
LMArena Text: Russian14011430Qwen3.5 397B A17B
LMArena Text: Polish13901447Qwen3.5 397B A17B
LMArena Text: multi-turn14061446Qwen3.5 397B A17B
LMArena Text: longer queries14001441Qwen3.5 397B A17B
LMArena Text: writing and language13881415Qwen3.5 397B A17B
LMArena Text: entertainment and media13701399Qwen3.5 397B A17B
LMArena Vision: EnglishNot measured1268Only Qwen3.5 397B A17B measured
LMArena Vision: ChineseNot measured1314Only Qwen3.5 397B A17B measured
LMArena Vision: reading textNot measured1271Only Qwen3.5 397B A17B measured
LMArena Vision: humorNot measured1262Only Qwen3.5 397B A17B measured
LMArena Vision: captioningNot measured1230Only Qwen3.5 397B A17B measured
LMArena Vision: recognizing thingsNot measured1265Only Qwen3.5 397B A17B measured
LMArena Vision: creative writingNot measured1260Only Qwen3.5 397B A17B measured
Neither model has a result on the other 17 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for Qwen3 235B A22B Thinking 2507 and Qwen3.5 397B A17B
BenchmarkQwen3 235B A22B Thinking 2507Qwen3.5 397B A17BLeader
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 235B A22B Thinking 2507$0.0022Fits in one request
Qwen3.5 397B A17B$0.0016Fits in one request

Qwen3.5 397B A17B costs less

Repository review

50K input + 3K output tokens

Qwen3 235B A22B Thinking 2507$0.033Fits in one request
Qwen3.5 397B A17B$0.027Fits in one request

Qwen3.5 397B A17B costs less

Agent loop

200K input + 10K output tokens

Qwen3 235B A22B Thinking 2507$0.125Exceeds the context window
Qwen3.5 397B A17B$0.101Fits in one request

Qwen3.5 397B A17B 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 235B A22B Thinking 2507 and Qwen3.5 397B A17B
SpecificationQwen3 235B A22B Thinking 2507Qwen3.5 397B A17B
MakerQwenQwen
WeightsOpen weightsOpen weights
ReleasedJuly 25, 2025February 16, 2026
Context window128K262K
Input $/Mtok$0.45$0.39
Output $/Mtok$3.50$2.34
Coding indexNot benchmarkedNot benchmarked
Independent measurements behind it01
Cost per solved taskNot computableNot computable
SourceOpenRouter listingOpenRouter listing

Questions

Is Qwen3 235B A22B Thinking 2507 better than Qwen3.5 397B A17B for coding?

Neither model has a coding score yet, so the two cannot be ranked on coding. Pick Qwen3 235B A22B Thinking 2507 for work measured by LMArena Text: coding or LMArena Text: software and IT, where it leads.

Which is cheaper, Qwen3 235B A22B Thinking 2507 or Qwen3.5 397B A17B?

Qwen3 235B A22B Thinking 2507 costs $0.45 per million input tokens and $3.50 per million output tokens; Qwen3.5 397B A17B costs $0.39 and $2.34. Cost per solved task is known for neither of them.

Which has the bigger context window, Qwen3 235B A22B Thinking 2507 or Qwen3.5 397B A17B?

Qwen3.5 397B A17B, with 262K tokens against 128K.

How many benchmarks is the Qwen3 235B A22B Thinking 2507 vs Qwen3.5 397B A17B comparison based on?

39 benchmarks have a result for both models as of October 22, 2026. Qwen3 235B A22B Thinking 2507's coding index rests on 0 independent benchmarks and Qwen3.5 397B A17B's on 1. Where only one model has a result, the page says so instead of naming a winner.

Compare next