Enter opens the highlighted result. Esc closes.

Qwen3.7 Plus vs Qwen3.8 27B

Qwen3.8 27B leads Qwen3.7 Plus on coding, 74.2 to 33.2 on the Vibe Coding Index, and Qwen3.7 Plus costs 2.0x less per output token ($1.28 vs $2.55 per million). Updated October 22, 2026; 56 benchmarks have a result for both.

Replace Qwen3.7 Plus Replace Qwen3.8 27B
Qwen3.7 PlusQwen
Coding
33.2
Overall
54.0
Output $/M
$1.28
33
Qwen3.8 27BQwen
Coding
74.2
Overall
59.6
Output $/M
$2.55
23
vs boards won of 56 shared

Qwen3.7 Plus or Qwen3.8 27B: which to pick

Pick Qwen3.8 27B for coding: it scores 74.2 on the Vibe Coding Index against 33.2 for Qwen3.7 Plus.

Pick Qwen3.7 Plus for output tokens 2.0x cheaper ($1.28 vs $2.55 per million) and work measured by SkillsBench (Vals AI) or Humanity's Last Exam (Artificial Analysis run), where it leads.

Model AQwen3.7 PlusQwen33.2/1002 independent benchmarksNo cost per solved taskModel BQwen3.8 27BQwen74.2/1004 independent benchmarks$1.26 per solved task
Shared results
56
Qwen3.7 Plus only
19
Qwen3.8 27B only
29
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, Qwen3.8 27B 74.2 from 4 benchmarks.
Widest category
Agentic work, 17.8 points apart on average over 5 shared benchmarks.
Widest single gap
AA Agentic Index: Qwen3.7 Plus 17.5 against Qwen3.8 27B 45.8, 28.3 points apart on a 0 to 100 scale.
Output price
Qwen3.7 Plus $1.28 against Qwen3.8 27B $2.55 per million output tokens, 2.0x 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
CategoryQwen3.7 PlusBarsQwen3.8 27BTies
Coding17
Intelligence02
Agentic work05
Reasoning43
Math20
Knowledge32
General234
All shared boards3323
CodingLike-for-likeSix of these boards feed the Vibe Coding Index17
Coding benchmarks for Qwen3.7 Plus and Qwen3.8 27B
BenchmarkQwen3.7 PlusQwen3.8 27BLeader
LiveBench codingNot measured86.8%Only Qwen3.8 27B measured
LMArena WebDevNot measured1593Only Qwen3.8 27B measured
AA Coding Index55.968.1Qwen3.8 27B
LiveCodeBench (Vals AI)Not measured84.0%Only Qwen3.8 27B measured
SWE-bench Verified (Vals AI)Not measured86.0%Only Qwen3.8 27B measured
Vibe Code Bench (Vals AI)46.4%64.8%Qwen3.8 27B
Code migration (Vals AI)12.9%14.2%Qwen3.8 27B
ProgramBench (Vals AI)Not measured0.0%Only Qwen3.8 27B measured
IOI (Vals AI)Not measured39.1%Only Qwen3.8 27B measured
Terminal-Bench 2.1 (Vals AI)52.8%58.4%Qwen3.8 27B
SkillsBench (Vals AI)54.3%38.1%Qwen3.7 Plus
CyberBench (Vals AI)Not measured67.8%Only Qwen3.8 27B measured
SciCode46.1%46.6%Qwen3.8 27B
Terminal-Bench Hard (Artificial Analysis run)47.0%Not measuredOnly Qwen3.7 Plus measured
FrontierCode10.2%Not measuredOnly Qwen3.7 Plus measured
LMArena Text: coding14731483Qwen3.8 27B
LMArena Text: software and IT14731478Qwen3.8 27B
LMArena WebDev: ReactNot measured1602Only Qwen3.8 27B measured
LMArena WebDev: HTMLNot measured1570Only Qwen3.8 27B measured
LMArena WebDev: from an imageNot measured1577Only Qwen3.8 27B measured
Neither model has a result on the other 19 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index02
Intelligence benchmarks for Qwen3.7 Plus and Qwen3.8 27B
BenchmarkQwen3.7 PlusQwen3.8 27BLeader
AA Intelligence Index25.233.7Qwen3.8 27B
Epoch Capabilities Index147.0151.7Qwen3.8 27B
Agentic workLike-for-likePublic boards, shown as published, kept out of the index05
Agentic work benchmarks for Qwen3.7 Plus and Qwen3.8 27B
BenchmarkQwen3.7 PlusQwen3.8 27BLeader
AA Agentic Index17.545.8Qwen3.8 27B
LiveBench researchNot measured59.4%Only Qwen3.8 27B measured
LiveBench browserNot measured32.0%Only Qwen3.8 27B measured
LiveBench long agenticNot measured27.9%Only Qwen3.8 27B measured
Finance Agent (Vals AI)38.2%48.5%Qwen3.8 27B
Tax Agent Bench (Vals AI)10.5%30.9%Qwen3.8 27B
Legal Research Bench (Vals AI)16.4%36.1%Qwen3.8 27B
Excel Modeling Benchmark (Vals AI)49.3%59.7%Qwen3.8 27B
Terminal-Bench-Science (Vals AI)Not measured0.0%Only Qwen3.8 27B measured
τ²-Bench Telecom93.0%Not measuredOnly Qwen3.7 Plus measured
APEX-AgentsNot measured47.5%Only Qwen3.8 27B measured
OSWorld 2.02.8%Not measuredOnly Qwen3.7 Plus measured
Neither model has a result on the other 29 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index43
Reasoning benchmarks for Qwen3.7 Plus and Qwen3.8 27B
BenchmarkQwen3.7 PlusQwen3.8 27BLeader
GPQA DiamondNot measured88.9%Only Qwen3.8 27B measured
LiveBench reasoningNot measured80.0%Only Qwen3.8 27B measured
MMMU Pro (Vals AI)Not measured83.9%Only Qwen3.8 27B measured
GPQA Diamond (Artificial Analysis run)90.0%90.5%Qwen3.8 27B
Humanity's Last Exam (Artificial Analysis run)35.6%33.9%Qwen3.7 Plus
GPQA Diamond (Epoch AI run)87.9%Not measuredOnly Qwen3.7 Plus measured
ARC-AGINot measured87.5%Only Qwen3.8 27B measured
ARC-AGI-2Not measured42.4%Only Qwen3.8 27B measured
Mystery game puzzles17.0%Not measuredOnly Qwen3.7 Plus measured
LMArena Text: hard prompts14601459Qwen3.7 Plus
LMArena Text: expert14661479Qwen3.8 27B
LMArena Text: hard prompts in English14601461Qwen3.8 27B
LMArena Vision: diagrams12921285Qwen3.7 Plus
LMArena Vision: homework12951295Qwen3.7 Plus
Neither model has a result on the other 8 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index20
Math benchmarks for Qwen3.7 Plus and Qwen3.8 27B
BenchmarkQwen3.7 PlusQwen3.8 27BLeader
OTIS Mock AIME93.3%Not measuredOnly Qwen3.7 Plus measured
FrontierMath, tiers 1 to 334.4%Not measuredOnly Qwen3.7 Plus measured
ProofBenchNot measured16.0%Only Qwen3.8 27B measured
LMArena Text: math14671455Qwen3.7 Plus
LMArena Text: mathematical work14701458Qwen3.7 Plus
Neither model has a result on the other 8 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index32
Knowledge benchmarks for Qwen3.7 Plus and Qwen3.8 27B
BenchmarkQwen3.7 PlusQwen3.8 27BLeader
MMLU ProNot measured84.3%Only Qwen3.8 27B measured
LegalBench (Vals AI)Not measured82.4%Only Qwen3.8 27B measured
TaxEval (Vals AI)Not measured70.8%Only Qwen3.8 27B measured
MortgageTax (Vals AI)66.2%64.9%Qwen3.7 Plus
MedCode (Vals AI)Not measured28.7%Only Qwen3.8 27B measured
LMArena Text: science14641467Qwen3.8 27B
LMArena Text: medicine and healthcare14641437Qwen3.7 Plus
LMArena Text: legal and government14511447Qwen3.7 Plus
LMArena Text: business and finance14351438Qwen3.8 27B
Neither model has a result on the other 9 boards here
Web designDirectional onlyPublic boards, shown as published, kept out of the index9 boards, none shared
Web design benchmarks for Qwen3.7 Plus and Qwen3.8 27B
BenchmarkQwen3.7 PlusQwen3.8 27BLeader
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
LiveBench designNot measured75.9%Only Qwen3.8 27B measured
GeneralLike-for-likePublic boards, shown as published, kept out of the index234
General benchmarks for Qwen3.7 Plus and Qwen3.8 27B
BenchmarkQwen3.7 PlusQwen3.8 27BLeader
LiveBench data analysisNot measured76.6%Only Qwen3.8 27B measured
SAGE (Vals AI)39.3%52.4%Qwen3.8 27B
MedScribe (Vals AI)Not measured83.8%Only Qwen3.8 27B measured
Vals Multimodal Index53.9%Not measuredOnly Qwen3.7 Plus measured
IFBench78.0%Not measuredOnly Qwen3.7 Plus measured
Long context reasoning (AA-LCR)73.0%82.0%Qwen3.8 27B
DTBench84.0%88.0%Qwen3.8 27B
LMCA37.6%41.4%Qwen3.8 27B
Surface Evolver BenchNot measured45.0%Only Qwen3.8 27B measured
LMArena Text14541440Qwen3.7 Plus
LMArena Text: instruction following14391436Qwen3.7 Plus
LMArena Text: creative writing14381383Qwen3.7 Plus
LMArena Vision12781269Qwen3.7 Plus
LMArena Text: English14581448Qwen3.7 Plus
LMArena Text: non-English14451428Qwen3.7 Plus
LMArena Text: Chinese15091501Qwen3.7 Plus
LMArena Text: German14711443Qwen3.7 Plus
LMArena Text: Japanese14121387Qwen3.7 Plus
LMArena Text: Korean14131384Qwen3.7 Plus
LMArena Text: French14721465Qwen3.7 Plus
LMArena Text: Spanish14571449Qwen3.7 Plus
LMArena Text: Russian14571415Qwen3.7 Plus
LMArena Text: Polish14491439Qwen3.7 Plus
LMArena Text: multi-turn14591440Qwen3.7 Plus
LMArena Text: longer queries14541448Qwen3.7 Plus
LMArena Text: writing and language14371405Qwen3.7 Plus
LMArena Text: entertainment and media14221393Qwen3.7 Plus
LMArena Vision: English12801267Qwen3.7 Plus
LMArena Vision: Chinese13321326Qwen3.7 Plus
LMArena Vision: reading text12881281Qwen3.7 Plus
LMArena Vision: humor12611235Qwen3.7 Plus
LMArena Vision: creative writing12581237Qwen3.7 Plus
LMArena Document1444Not measuredOnly Qwen3.7 Plus measured
Neither model has a result on the other 13 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 Qwen3.8 27B
BenchmarkQwen3.7 PlusQwen3.8 27BLeader
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
Qwen3.8 27B$0.0017Fits in one request

Qwen3.7 Plus costs less

Repository review

50K input + 3K output tokens

Qwen3.7 Plus$0.020Fits in one request
Qwen3.8 27B$0.029Fits in one request

Qwen3.7 Plus costs less

Agent loop

200K input + 10K output tokens

Qwen3.7 Plus$0.077Fits in one request
Qwen3.8 27B$0.111Fits 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 Qwen3.7 Plus and Qwen3.8 27B
SpecificationQwen3.7 PlusQwen3.8 27B
MakerQwenQwen
WeightsNo public weights listedOpen weights
ReleasedJune 3, 2026August 14, 2026
Context window1M1M
Input $/Mtok$0.32$0.425
Output $/Mtok$1.28$2.55
Coding index33.274.2
Independent measurements behind it24
Cost per solved taskNot computable$1.26
SourceOpenRouter listingOpenRouter listing

Questions

Is Qwen3.7 Plus better than Qwen3.8 27B for coding?

Pick Qwen3.8 27B for coding: it scores 74.2 on the Vibe Coding Index against 33.2 for Qwen3.7 Plus. Pick Qwen3.7 Plus for output tokens 2.0x cheaper ($1.28 vs $2.55 per million) and work measured by SkillsBench (Vals AI) or Humanity's Last Exam (Artificial Analysis run), where it leads.

Which is cheaper, Qwen3.7 Plus or Qwen3.8 27B?

Qwen3.7 Plus costs $0.32 per million input tokens and $1.28 per million output tokens; Qwen3.8 27B costs $0.425 and $2.55. Cost per solved task is known for Qwen3.8 27B only.

Which has the bigger context window, Qwen3.7 Plus or Qwen3.8 27B?

Neither: both take 1M tokens.

How many benchmarks is the Qwen3.7 Plus vs Qwen3.8 27B comparison based on?

56 benchmarks have a result for both models as of October 22, 2026. Qwen3.7 Plus's coding index rests on 2 independent benchmarks and Qwen3.8 27B's on 4. 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/qwen3-7-plus-vs-qwen3-8-27b" title="Qwen3.7 Plus vs Qwen3.8 27B, 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/qwen3-7-plus-vs-qwen3-8-27b">LLMBenchmark.ai, Qwen3.7 Plus vs Qwen3.8 27B</a></p>