Enter opens the highlighted result. Esc closes.

Qwen3.7 Plus vs Qwen3 VL 235B A22B Instruct

Qwen3.7 Plus leads Qwen3 VL 235B A22B Instruct on the Artificial Analysis Intelligence Index, 25.2 to 9.9, and Qwen3.7 Plus costs 1.5x less per output token ($1.28 vs $1.90 per million). Updated October 22, 2026; 43 benchmarks have a result for both.

Replace Qwen3.7 Plus Replace Qwen3 VL 235B A22B Instruct
Qwen3.7 PlusQwen
Coding
33.2
Overall
54.0
Output $/M
$1.28
43
Qwen3 VL 235B A22B InstructQwen
Coding
No data
Overall
No data
Output $/M
$1.90
0
vs boards won of 43 shared

Qwen3.7 Plus or Qwen3 VL 235B A22B Instruct: which to pick

Only Qwen3.7 Plus has a coding score, 33.2 on the Vibe Coding Index; Qwen3 VL 235B A22B Instruct has none, so the two cannot be ranked on coding.

Compare them on price, context and the boards below.

Model AQwen3.7 PlusQwen33.2/1002 independent benchmarksNo cost per solved taskModel BQwen3 VL 235B A22B InstructQwenNot benchmarkedNo coding benchmarkNo cost per solved task
Shared results
43
Qwen3.7 Plus only
32
Qwen3 VL 235B A22B Instruct only
6
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
Qwen3.7 Plus 33.2 from 2 benchmarks, Qwen3 VL 235B A22B Instruct not benchmarked.
Widest category
Agentic work, 38.9 points apart on average over 1 shared benchmark.
Widest single gap
τ²-Bench Telecom: Qwen3.7 Plus 93.0% against Qwen3 VL 235B A22B Instruct 54.1%, 38.9 points apart on a 0 to 100 scale.
Output price
Qwen3.7 Plus $1.28 against Qwen3 VL 235B A22B Instruct $1.90 per million output tokens, 1.5x apart.
Context window
Qwen3.7 Plus takes 1M tokens, Qwen3 VL 235B A22B Instruct 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
CategoryQwen3.7 PlusBarsQwen3 VL 235B A22B InstructTies
Coding30
Intelligence10
Agentic work10
Reasoning70
Math20
Knowledge40
General250
All shared boards430
CodingLike-for-likeSix of these boards feed the Vibe Coding Index30
Coding benchmarks for Qwen3.7 Plus and Qwen3 VL 235B A22B Instruct
BenchmarkQwen3.7 PlusQwen3 VL 235B A22B InstructLeader
AA Coding Index55.9Not measuredOnly Qwen3.7 Plus measured
Vibe Code Bench (Vals AI)46.4%Not measuredOnly Qwen3.7 Plus measured
Code migration (Vals AI)12.9%Not measuredOnly Qwen3.7 Plus measured
Terminal-Bench 2.1 (Vals AI)52.8%Not measuredOnly Qwen3.7 Plus measured
SkillsBench (Vals AI)54.3%Not measuredOnly Qwen3.7 Plus measured
LiveCodeBench (Artificial Analysis run)Not measured64.6%Only Qwen3 VL 235B A22B Instruct measured
SciCode46.1%Not measuredOnly Qwen3.7 Plus measured
Terminal-Bench Hard (Artificial Analysis run)47.0%11.4%Qwen3.7 Plus
FrontierCode10.2%Not measuredOnly Qwen3.7 Plus measured
LMArena Text: coding14731438Qwen3.7 Plus
LMArena Text: software and IT14731442Qwen3.7 Plus
Neither model has a result on the other 28 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index10
Intelligence benchmarks for Qwen3.7 Plus and Qwen3 VL 235B A22B Instruct
BenchmarkQwen3.7 PlusQwen3 VL 235B A22B InstructLeader
AA Intelligence Index25.29.9Qwen3.7 Plus
Epoch Capabilities Index147.0Not measuredOnly Qwen3.7 Plus measured
Agentic workLike-for-likePublic boards, shown as published, kept out of the index10
Agentic work benchmarks for Qwen3.7 Plus and Qwen3 VL 235B A22B Instruct
BenchmarkQwen3.7 PlusQwen3 VL 235B A22B InstructLeader
AA Agentic Index17.5Not measuredOnly Qwen3.7 Plus measured
Finance Agent (Vals AI)38.2%Not measuredOnly Qwen3.7 Plus measured
Tax Agent Bench (Vals AI)10.5%Not measuredOnly Qwen3.7 Plus measured
Legal Research Bench (Vals AI)16.4%Not measuredOnly Qwen3.7 Plus measured
Excel Modeling Benchmark (Vals AI)49.3%Not measuredOnly Qwen3.7 Plus measured
τ²-Bench Telecom93.0%54.1%Qwen3.7 Plus
OSWorld 2.02.8%Not measuredOnly Qwen3.7 Plus measured
Neither model has a result on the other 34 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index70
Reasoning benchmarks for Qwen3.7 Plus and Qwen3 VL 235B A22B Instruct
BenchmarkQwen3.7 PlusQwen3 VL 235B A22B InstructLeader
GPQA Diamond (Artificial Analysis run)90.0%77.2%Qwen3.7 Plus
Humanity's Last Exam (Artificial Analysis run)35.6%11.9%Qwen3.7 Plus
GPQA Diamond (Epoch AI run)87.9%Not measuredOnly Qwen3.7 Plus measured
Mystery game puzzles17.0%Not measuredOnly Qwen3.7 Plus measured
LMArena Text: hard prompts14601428Qwen3.7 Plus
LMArena Text: expert14661442Qwen3.7 Plus
LMArena Text: hard prompts in English14601439Qwen3.7 Plus
LMArena Vision: diagrams12921255Qwen3.7 Plus
LMArena Vision: homework12951277Qwen3.7 Plus
Neither model has a result on the other 13 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index20
Math benchmarks for Qwen3.7 Plus and Qwen3 VL 235B A22B Instruct
BenchmarkQwen3.7 PlusQwen3 VL 235B A22B InstructLeader
AA Math IndexNot measured88.3Only Qwen3 VL 235B A22B Instruct measured
AIME 2025 (Artificial Analysis run)Not measured88.3%Only Qwen3 VL 235B A22B Instruct measured
OTIS Mock AIME93.3%Not measuredOnly Qwen3.7 Plus measured
FrontierMath, tiers 1 to 334.4%Not measuredOnly Qwen3.7 Plus measured
LMArena Text: math14671425Qwen3.7 Plus
LMArena Text: mathematical work14701419Qwen3.7 Plus
Neither model has a result on the other 7 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index40
Knowledge benchmarks for Qwen3.7 Plus and Qwen3 VL 235B A22B Instruct
BenchmarkQwen3.7 PlusQwen3 VL 235B A22B InstructLeader
MortgageTax (Vals AI)66.2%Not measuredOnly Qwen3.7 Plus measured
MMLU Pro (Artificial Analysis run)Not measured83.6%Only Qwen3 VL 235B A22B Instruct measured
LMArena Text: science14641444Qwen3.7 Plus
LMArena Text: medicine and healthcare14641431Qwen3.7 Plus
LMArena Text: legal and government14511438Qwen3.7 Plus
LMArena Text: business and finance14351433Qwen3.7 Plus
Neither model has a result on the other 12 boards here
Web designDirectional onlyPublic boards, shown as published, kept out of the index8 boards, none shared
Web design benchmarks for Qwen3.7 Plus and Qwen3 VL 235B A22B Instruct
BenchmarkQwen3.7 PlusQwen3 VL 235B A22B InstructLeader
Design Arena: websites1269Not measuredOnly Qwen3.7 Plus measured
Design Arena: UI components1258Not measuredOnly Qwen3.7 Plus measured
Design Arena: game dev1261Not measuredOnly Qwen3.7 Plus measured
Design Arena: data viz1276Not measuredOnly Qwen3.7 Plus measured
Design Arena: 3D1238Not measuredOnly Qwen3.7 Plus measured
Design Arena: all code categories1269Not measuredOnly Qwen3.7 Plus measured
Design Arena: SVG1208Not measuredOnly Qwen3.7 Plus measured
Design Arena: ASCII art1143Not measuredOnly Qwen3.7 Plus measured
Neither model has a result on the other 1 board here
GeneralLike-for-likePublic boards, shown as published, kept out of the index250
General benchmarks for Qwen3.7 Plus and Qwen3 VL 235B A22B Instruct
BenchmarkQwen3.7 PlusQwen3 VL 235B A22B InstructLeader
SAGE (Vals AI)39.3%Not measuredOnly Qwen3.7 Plus measured
Vals Multimodal Index53.9%Not measuredOnly Qwen3.7 Plus measured
IFBench78.0%56.5%Qwen3.7 Plus
Long context reasoning (AA-LCR)73.0%63.7%Qwen3.7 Plus
DTBench84.0%Not measuredOnly Qwen3.7 Plus measured
LMCA37.6%Not measuredOnly Qwen3.7 Plus measured
LMArena Text14541420Qwen3.7 Plus
LMArena Text: instruction following14391406Qwen3.7 Plus
LMArena Text: creative writing14381366Qwen3.7 Plus
LMArena Vision12781247Qwen3.7 Plus
LMArena Text: English14581429Qwen3.7 Plus
LMArena Text: non-English14451405Qwen3.7 Plus
LMArena Text: Chinese15091463Qwen3.7 Plus
LMArena Text: German14711424Qwen3.7 Plus
LMArena Text: Japanese14121385Qwen3.7 Plus
LMArena Text: Korean14131394Qwen3.7 Plus
LMArena Text: French14721452Qwen3.7 Plus
LMArena Text: Spanish14571428Qwen3.7 Plus
LMArena Text: Russian14571408Qwen3.7 Plus
LMArena Text: Polish14491419Qwen3.7 Plus
LMArena Text: multi-turn14591428Qwen3.7 Plus
LMArena Text: longer queries14541419Qwen3.7 Plus
LMArena Text: writing and language14371392Qwen3.7 Plus
LMArena Text: entertainment and media14221368Qwen3.7 Plus
LMArena Vision: English12801256Qwen3.7 Plus
LMArena Vision: Chinese13321283Qwen3.7 Plus
LMArena Vision: reading text12881253Qwen3.7 Plus
LMArena Vision: humor12611209Qwen3.7 Plus
LMArena Vision: captioningNot measured1281Only Qwen3 VL 235B A22B Instruct measured
LMArena Vision: recognizing thingsNot measured1249Only Qwen3 VL 235B A22B Instruct measured
LMArena Vision: creative writing12581220Qwen3.7 Plus
LMArena Document1444Not measuredOnly Qwen3.7 Plus measured
Neither model has a result on the other 14 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for Qwen3.7 Plus and Qwen3 VL 235B A22B Instruct
BenchmarkQwen3.7 PlusQwen3 VL 235B A22B InstructLeader
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

Qwen3.7 Plus$0.0010Fits in one request
Qwen3 VL 235B A22B Instruct$0.0012Fits in one request

Qwen3.7 Plus costs less

Repository review

50K input + 3K output tokens

Qwen3.7 Plus$0.020Fits in one request
Qwen3 VL 235B A22B Instruct$0.016Fits in one request

Qwen3 VL 235B A22B Instruct costs less

Agent loop

200K input + 10K output tokens

Qwen3.7 Plus$0.077Fits in one request
Qwen3 VL 235B A22B Instruct$0.061Fits in one request

Qwen3 VL 235B A22B Instruct 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 Qwen3.7 Plus and Qwen3 VL 235B A22B Instruct
SpecificationQwen3.7 PlusQwen3 VL 235B A22B Instruct
MakerQwenQwen
WeightsNo public weights listedOpen weights
ReleasedJune 3, 2026September 23, 2025
Context window1M262K
Input $/Mtok$0.32$0.21
Output $/Mtok$1.28$1.90
Coding index33.2Not benchmarked
Independent measurements behind it20
Cost per solved taskNot computableNot computable
SourceOpenRouter listingOpenRouter listing

Questions

Is Qwen3.7 Plus better than Qwen3 VL 235B A22B Instruct for coding?

Only Qwen3.7 Plus has a coding score, 33.2 on the Vibe Coding Index; Qwen3 VL 235B A22B Instruct has none, so the two cannot be ranked on coding. Compare them on price, context and the boards below.

Which is cheaper, Qwen3.7 Plus or Qwen3 VL 235B A22B Instruct?

Qwen3.7 Plus costs $0.32 per million input tokens and $1.28 per million output tokens; Qwen3 VL 235B A22B Instruct costs $0.21 and $1.90. Cost per solved task is known for neither of them.

Which has the bigger context window, Qwen3.7 Plus or Qwen3 VL 235B A22B Instruct?

Qwen3.7 Plus, with 1M tokens against 262K.

How many benchmarks is the Qwen3.7 Plus vs Qwen3 VL 235B A22B Instruct comparison based on?

43 benchmarks have a result for both models as of October 22, 2026. Qwen3.7 Plus's coding index rests on 2 independent benchmarks and Qwen3 VL 235B A22B Instruct's on 0. Where only one model has a result, the page says so instead of naming a winner.

Compare next