Enter opens the highlighted result. Esc closes.

Qwen3.6 Plus vs Qwen3.7 Plus

Qwen3.6 Plus leads Qwen3.7 Plus on coding, 44.1 to 33.2 on the Vibe Coding Index, and Qwen3.7 Plus costs 1.5x less per output token ($1.28 vs $1.95 per million). Updated October 21, 2026; 61 benchmarks have a result for both.

Replace Qwen3.6 Plus Replace Qwen3.7 Plus
Qwen3.6 PlusQwen
Coding
44.1
Overall
56.2
Output $/M
$1.95
10
Qwen3.7 PlusQwen
Coding
33.2
Overall
54.0
Output $/M
$1.28
50
vs boards won of 61 shared, 1 tied

Qwen3.6 Plus or Qwen3.7 Plus: which to pick

Pick Qwen3.6 Plus for coding: it scores 44.1 on the Vibe Coding Index against 33.2 for Qwen3.7 Plus.

Pick Qwen3.7 Plus for output tokens 1.5x cheaper ($1.28 vs $1.95 per million) and work measured by AA Coding Index or Vibe Code Bench (Vals AI), where it leads.

Model AQwen3.6 PlusQwen44.1/1003 independent benchmarks$1.19 per solved taskModel BQwen3.7 PlusQwen33.2/1002 independent benchmarksNo cost per solved task
Shared results
61
Qwen3.6 Plus only
22
Qwen3.7 Plus only
14
Like-for-like categories
8 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
Qwen3.6 Plus 44.1 from 3 benchmarks, Qwen3.7 Plus 33.2 from 2 benchmarks.
Widest category
Agentic work, 5.6 points apart on average over 5 shared benchmarks.
Widest single gap
Vibe Code Bench (Vals AI): Qwen3.6 Plus 25.6% against Qwen3.7 Plus 46.4%, 20.8 points apart on a 0 to 100 scale.
Output price
Qwen3.6 Plus $1.95 against Qwen3.7 Plus $1.28 per million output tokens, 1.5x apart.
Context window
Both take 1M tokens.

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
CategoryQwen3.6 PlusBarsQwen3.7 PlusTies
Coding16
Intelligence20
Agentic work23
Reasoning16
Math121 tie
Knowledge14
Web design08
General221
All shared boards10501 tie
CodingLike-for-likeSix of these boards feed the Vibe Coding Index16
Coding benchmarks for Qwen3.6 Plus and Qwen3.7 Plus
BenchmarkQwen3.6 PlusQwen3.7 PlusLeader
LMArena WebDev1461Not measuredOnly Qwen3.6 Plus measured
AA Coding Index54.555.9Qwen3.7 Plus
LiveCodeBench (Vals AI)86.0%Not measuredOnly Qwen3.6 Plus measured
SWE-bench Verified (Vals AI)73.4%Not measuredOnly Qwen3.6 Plus measured
Vibe Code Bench (Vals AI)25.6%46.4%Qwen3.7 Plus
Code migration (Vals AI)11.1%12.9%Qwen3.7 Plus
ProgramBench (Vals AI)0.0%Not measuredOnly Qwen3.6 Plus measured
Terminal-Bench 2.1 (Vals AI)53.2%52.8%Qwen3.6 Plus
SkillsBench (Vals AI)Not measured54.3%Only Qwen3.7 Plus measured
SciCodeNot measured46.1%Only Qwen3.7 Plus measured
Terminal-Bench Hard (Artificial Analysis run)43.9%47.0%Qwen3.7 Plus
FrontierCodeNot measured10.2%Only Qwen3.7 Plus measured
ALE-Bench670.1Not measuredOnly Qwen3.6 Plus measured
LMArena Text: coding14671473Qwen3.7 Plus
LMArena Text: software and IT14621473Qwen3.7 Plus
LMArena WebDev: React1454Not measuredOnly Qwen3.6 Plus measured
LMArena WebDev: HTML1463Not measuredOnly Qwen3.6 Plus measured
LMArena WebDev: from an image1472Not measuredOnly Qwen3.6 Plus measured
Neither model has a result on the other 21 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
Intelligence benchmarks for Qwen3.6 Plus and Qwen3.7 Plus
BenchmarkQwen3.6 PlusQwen3.7 PlusLeader
AA Intelligence Index27.025.2Qwen3.6 Plus
Epoch Capabilities Index147.3147.0Qwen3.6 Plus
Agentic workLike-for-likePublic boards, shown as published, kept out of the index23
Agentic work benchmarks for Qwen3.6 Plus and Qwen3.7 Plus
BenchmarkQwen3.6 PlusQwen3.7 PlusLeader
AA Agentic IndexNot measured17.5Only Qwen3.7 Plus measured
Finance Agent (Vals AI)40.9%38.2%Qwen3.6 Plus
Tax Agent Bench (Vals AI)7.7%10.5%Qwen3.7 Plus
Legal Research Bench (Vals AI)14.9%16.4%Qwen3.7 Plus
Excel Modeling Benchmark (Vals AI)32.9%49.3%Qwen3.7 Plus
τ²-Bench Telecom97.7%93.0%Qwen3.6 Plus
OSWorld 2.0Not measured2.8%Only Qwen3.7 Plus measured
Vending-Bench 2$5,115Not measuredOnly Qwen3.6 Plus measured
Neither model has a result on the other 33 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index16
Reasoning benchmarks for Qwen3.6 Plus and Qwen3.7 Plus
BenchmarkQwen3.6 PlusQwen3.7 PlusLeader
GPQA Diamond87.4%Not measuredOnly Qwen3.6 Plus measured
MMMU Pro (Vals AI)84.2%Not measuredOnly Qwen3.6 Plus measured
GPQA Diamond (Artificial Analysis run)88.2%90.0%Qwen3.7 Plus
Humanity's Last Exam (Artificial Analysis run)27.8%35.6%Qwen3.7 Plus
GPQA Diamond (Epoch AI run)88.4%87.9%Qwen3.6 Plus
Chess puzzles14.0%Not measuredOnly Qwen3.6 Plus measured
Mystery game puzzles12.0%17.0%Qwen3.7 Plus
LMArena Text: hard prompts14481460Qwen3.7 Plus
LMArena Text: expert14541466Qwen3.7 Plus
LMArena Text: hard prompts in English14551460Qwen3.7 Plus
LMArena Vision: diagramsNot measured1292Only Qwen3.7 Plus measured
LMArena Vision: homeworkNot measured1295Only Qwen3.7 Plus measured
Neither model has a result on the other 10 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index12
Math benchmarks for Qwen3.6 Plus and Qwen3.7 Plus
BenchmarkQwen3.6 PlusQwen3.7 PlusLeader
AIME94.6%Not measuredOnly Qwen3.6 Plus measured
OTIS Mock AIME93.3%93.3%Tie
FrontierMath, tiers 1 to 338.2%34.4%Qwen3.6 Plus
LMArena Text: math14491467Qwen3.7 Plus
LMArena Text: mathematical work14481470Qwen3.7 Plus
Neither model has a result on the other 8 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index14
Knowledge benchmarks for Qwen3.6 Plus and Qwen3.7 Plus
BenchmarkQwen3.6 PlusQwen3.7 PlusLeader
MMLU Pro87.7%Not measuredOnly Qwen3.6 Plus measured
LegalBench (Vals AI)84.2%Not measuredOnly Qwen3.6 Plus measured
CaseLaw (Vals AI)51.5%Not measuredOnly Qwen3.6 Plus measured
CorpFin (Vals AI)61.9%Not measuredOnly Qwen3.6 Plus measured
TaxEval (Vals AI)74.7%Not measuredOnly Qwen3.6 Plus measured
MortgageTax (Vals AI)68.0%66.2%Qwen3.6 Plus
MedCode (Vals AI)36.9%Not measuredOnly Qwen3.6 Plus measured
SimpleQA Verified44.1%Not measuredOnly Qwen3.6 Plus measured
LMArena Text: science14391464Qwen3.7 Plus
LMArena Text: medicine and healthcare14421464Qwen3.7 Plus
LMArena Text: legal and government14371451Qwen3.7 Plus
LMArena Text: business and finance14301435Qwen3.7 Plus
Neither model has a result on the other 6 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index08
Web design benchmarks for Qwen3.6 Plus and Qwen3.7 Plus
BenchmarkQwen3.6 PlusQwen3.7 PlusLeader
Design Arena: websites12431269Qwen3.7 Plus
Design Arena: UI components12331261Qwen3.7 Plus
Design Arena: game dev12111262Qwen3.7 Plus
Design Arena: data viz12281276Qwen3.7 Plus
Design Arena: 3D12021239Qwen3.7 Plus
Design Arena: all code categories12361269Qwen3.7 Plus
Design Arena: SVG11611208Qwen3.7 Plus
Design Arena: ASCII art11131143Qwen3.7 Plus
Neither model has a result on the other 1 board here
GeneralLike-for-likePublic boards, shown as published, kept out of the index221
General benchmarks for Qwen3.6 Plus and Qwen3.7 Plus
BenchmarkQwen3.6 PlusQwen3.7 PlusLeader
SAGE (Vals AI)44.9%39.3%Qwen3.6 Plus
MedScribe (Vals AI)77.0%Not measuredOnly Qwen3.6 Plus measured
Vals Multimodal Index51.5%53.9%Qwen3.7 Plus
IFBench75.2%78.0%Qwen3.7 Plus
Long context reasoning (AA-LCR)78.3%73.0%Qwen3.6 Plus
DTBench81.9%84.0%Qwen3.7 Plus
LMCA33.1%37.6%Qwen3.7 Plus
CL-bench20.3%Not measuredOnly Qwen3.6 Plus measured
LMArena Text14361454Qwen3.7 Plus
LMArena Text: instruction following14241439Qwen3.7 Plus
LMArena Text: creative writing14041438Qwen3.7 Plus
LMArena VisionNot measured1278Only Qwen3.7 Plus measured
LMArena Text: English14451458Qwen3.7 Plus
LMArena Text: non-English14241445Qwen3.7 Plus
LMArena Text: Chinese14771509Qwen3.7 Plus
LMArena Text: German14511471Qwen3.7 Plus
LMArena Text: Japanese13901412Qwen3.7 Plus
LMArena Text: Korean13791413Qwen3.7 Plus
LMArena Text: French14551472Qwen3.7 Plus
LMArena Text: Spanish14321457Qwen3.7 Plus
LMArena Text: Russian14341457Qwen3.7 Plus
LMArena Text: Polish14331449Qwen3.7 Plus
LMArena Text: multi-turn14381459Qwen3.7 Plus
LMArena Text: longer queries14391454Qwen3.7 Plus
LMArena Text: writing and language14181437Qwen3.7 Plus
LMArena Text: entertainment and media14021422Qwen3.7 Plus
LMArena Vision: EnglishNot measured1280Only Qwen3.7 Plus measured
LMArena Vision: ChineseNot measured1332Only Qwen3.7 Plus measured
LMArena Vision: reading textNot measured1288Only Qwen3.7 Plus measured
LMArena Vision: humorNot measured1261Only Qwen3.7 Plus measured
LMArena Vision: creative writingNot measured1258Only Qwen3.7 Plus measured
LMArena DocumentNot measured1444Only 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 Qwen3.6 Plus and Qwen3.7 Plus
BenchmarkQwen3.6 PlusQwen3.7 PlusLeader
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

Qwen3.6 Plus$0.0013Fits in one request
Qwen3.7 Plus$0.0010Fits in one request

Qwen3.7 Plus costs less

Repository review

50K input + 3K output tokens

Qwen3.6 Plus$0.022Fits in one request
Qwen3.7 Plus$0.020Fits in one request

Qwen3.7 Plus costs less

Agent loop

200K input + 10K output tokens

Qwen3.6 Plus$0.085Fits in one request
Qwen3.7 Plus$0.077Fits in one request

Qwen3.7 Plus 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 Qwen3.6 Plus and Qwen3.7 Plus
SpecificationQwen3.6 PlusQwen3.7 Plus
MakerQwenQwen
WeightsNo public weights listedNo public weights listed
ReleasedApril 2, 2026June 3, 2026
Context window1M1M
Input $/Mtok$0.325$0.32
Output $/Mtok$1.95$1.28
Coding index44.133.2
Independent measurements behind it32
Cost per solved task$1.19Not computable
SourceOpenRouter listingOpenRouter listing

Questions

Is Qwen3.6 Plus better than Qwen3.7 Plus for coding?

Pick Qwen3.6 Plus for coding: it scores 44.1 on the Vibe Coding Index against 33.2 for Qwen3.7 Plus. Pick Qwen3.7 Plus for output tokens 1.5x cheaper ($1.28 vs $1.95 per million) and work measured by AA Coding Index or Vibe Code Bench (Vals AI), where it leads.

Which is cheaper, Qwen3.6 Plus or Qwen3.7 Plus?

Qwen3.6 Plus costs $0.325 per million input tokens and $1.95 per million output tokens; Qwen3.7 Plus costs $0.32 and $1.28. Cost per solved task is known for Qwen3.6 Plus only.

Which has the bigger context window, Qwen3.6 Plus or Qwen3.7 Plus?

Neither: both take 1M tokens.

How many benchmarks is the Qwen3.6 Plus vs Qwen3.7 Plus comparison based on?

61 benchmarks have a result for both models as of October 21, 2026. Qwen3.6 Plus's coding index rests on 3 independent benchmarks and Qwen3.7 Plus's on 2. Where only one model has a result, the page says so instead of naming a winner.

Compare next

Embed this comparison on your site

Free under CC BY 4.0, while the source link stays visible. Preview the frame · Terms and other embeds

<iframe src="https://llmbenchmark.ai/embed/compare/qwen3-6-plus-vs-qwen3-7-plus" title="Qwen3.6 Plus vs Qwen3.7 Plus, LLMBenchmark.ai" width="100%" height="360" style="border:0;max-width:100%" loading="lazy"></iframe>
<p style="font:13px/1.4 sans-serif;margin:6px 0 0">Source: <a href="https://llmbenchmark.ai/compare/qwen3-6-plus-vs-qwen3-7-plus">LLMBenchmark.ai, Qwen3.6 Plus vs Qwen3.7 Plus</a></p>