Enter opens the highlighted result. Esc closes.

Gemma 4 31B vs Qwen3.7 Plus

Gemma 4 31B leads Qwen3.7 Plus on coding, 39.0 to 33.2 on the Vibe Coding Index, and Gemma 4 31B costs 3.2x less per output token ($0.40 vs $1.28 per million). Updated October 21, 2026; 51 benchmarks have a result for both.

Replace Gemma 4 31B Replace Qwen3.7 Plus
Gemma 4 31BGoogle
Coding
39.0
Overall
42.1
Output $/M
$0.40
6
Qwen3.7 PlusQwen
Coding
33.2
Overall
54.0
Output $/M
$1.28
45
vs boards won of 51 shared

Gemma 4 31B or Qwen3.7 Plus: which to pick

Pick Gemma 4 31B for coding: it scores 39.0 on the Vibe Coding Index against 33.2 for Qwen3.7 Plus.

Pick Qwen3.7 Plus for a larger context window (1M against 262K tokens) and work measured by AA Coding Index or SciCode, where it leads.

Model AGemma 4 31BGoogle39.0/1002 independent benchmarksNo cost per solved taskModel BQwen3.7 PlusQwen33.2/1002 independent benchmarksNo cost per solved task
Shared results
51
Gemma 4 31B only
20
Qwen3.7 Plus only
24
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
Gemma 4 31B 39.0 from 2 benchmarks, Qwen3.7 Plus 33.2 from 2 benchmarks.
Widest category
Agentic work, 20.4 points apart on average over 2 shared benchmarks.
Widest single gap
τ²-Bench Telecom: Gemma 4 31B 65.5% against Qwen3.7 Plus 93.0%, 27.5 points apart on a 0 to 100 scale.
Output price
Gemma 4 31B $0.40 against Qwen3.7 Plus $1.28 per million output tokens, 3.2x apart.
Context window
Gemma 4 31B takes 262K tokens, Qwen3.7 Plus 1M.

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
CategoryGemma 4 31BBarsQwen3.7 PlusTies
Coding05
Intelligence02
Agentic work02
Reasoning17
Math03
Knowledge05
General521
All shared boards645
CodingLike-for-likeSix of these boards feed the Vibe Coding Index05
Coding benchmarks for Gemma 4 31B and Qwen3.7 Plus
BenchmarkGemma 4 31BQwen3.7 PlusLeader
LiveBench coding49.0%Not measuredOnly Gemma 4 31B measured
LMArena WebDev1367Not measuredOnly Gemma 4 31B measured
AA Coding Index43.455.9Qwen3.7 Plus
Vibe Code Bench (Vals AI)Not measured46.4%Only Qwen3.7 Plus measured
Code migration (Vals AI)Not measured12.9%Only Qwen3.7 Plus measured
Terminal-Bench 2.1 (Vals AI)Not measured52.8%Only Qwen3.7 Plus measured
SkillsBench (Vals AI)Not measured54.3%Only Qwen3.7 Plus measured
SciCode45.5%46.1%Qwen3.7 Plus
Terminal-Bench Hard (Artificial Analysis run)36.4%47.0%Qwen3.7 Plus
FrontierCodeNot measured10.2%Only Qwen3.7 Plus measured
WeirdML52.3%Not measuredOnly Gemma 4 31B measured
ALE-Bench925.5Not measuredOnly Gemma 4 31B measured
LMArena Text: coding14591473Qwen3.7 Plus
LMArena Text: software and IT14631473Qwen3.7 Plus
LMArena WebDev: React1359Not measuredOnly Gemma 4 31B measured
LMArena WebDev: HTML1380Not measuredOnly Gemma 4 31B measured
SciCode8.9%Not measuredOnly Gemma 4 31B measured
Neither model has a result on the other 22 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index02
Intelligence benchmarks for Gemma 4 31B and Qwen3.7 Plus
BenchmarkGemma 4 31BQwen3.7 PlusLeader
AA Intelligence Index14.725.2Qwen3.7 Plus
Epoch Capabilities Index143.0147.0Qwen3.7 Plus
Agentic workLike-for-likePublic boards, shown as published, kept out of the index02
Agentic work benchmarks for Gemma 4 31B and Qwen3.7 Plus
BenchmarkGemma 4 31BQwen3.7 PlusLeader
AA Agentic Index4.217.5Qwen3.7 Plus
LiveBench research44.4%Not measuredOnly Gemma 4 31B measured
LiveBench browser4.0%Not measuredOnly Gemma 4 31B measured
LiveBench long agentic13.3%Not measuredOnly Gemma 4 31B measured
Finance Agent (Vals AI)Not measured38.2%Only Qwen3.7 Plus measured
Tax Agent Bench (Vals AI)Not measured10.5%Only Qwen3.7 Plus measured
Legal Research Bench (Vals AI)Not measured16.4%Only Qwen3.7 Plus measured
Excel Modeling Benchmark (Vals AI)Not measured49.3%Only Qwen3.7 Plus measured
τ²-Bench Telecom65.5%93.0%Qwen3.7 Plus
OSWorld 2.0Not measured2.8%Only Qwen3.7 Plus measured
Neither model has a result on the other 31 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index17
Reasoning benchmarks for Gemma 4 31B and Qwen3.7 Plus
BenchmarkGemma 4 31BQwen3.7 PlusLeader
LiveBench reasoning68.3%Not measuredOnly Gemma 4 31B measured
GPQA Diamond (Artificial Analysis run)85.7%90.0%Qwen3.7 Plus
Humanity's Last Exam (Artificial Analysis run)23.6%35.6%Qwen3.7 Plus
GPQA Diamond (Epoch AI run)75.8%87.9%Qwen3.7 Plus
Mystery game puzzlesNot measured17.0%Only Qwen3.7 Plus measured
LMArena Text: hard prompts14481460Qwen3.7 Plus
LMArena Text: expert14641466Qwen3.7 Plus
LMArena Text: hard prompts in English14561460Qwen3.7 Plus
LMArena Vision: diagrams12831292Qwen3.7 Plus
LMArena Vision: homework13101295Gemma 4 31B
Kagi LLM Benchmark63.5%Not measuredOnly Gemma 4 31B measured
Neither model has a result on the other 11 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index03
Math benchmarks for Gemma 4 31B and Qwen3.7 Plus
BenchmarkGemma 4 31BQwen3.7 PlusLeader
OTIS Mock AIME73.3%93.3%Qwen3.7 Plus
FrontierMath, tiers 1 to 3Not measured34.4%Only Qwen3.7 Plus measured
LMArena Text: math14631467Qwen3.7 Plus
LMArena Text: mathematical work14651470Qwen3.7 Plus
Neither model has a result on the other 9 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index05
Knowledge benchmarks for Gemma 4 31B and Qwen3.7 Plus
BenchmarkGemma 4 31BQwen3.7 PlusLeader
CaseLaw (Vals AI)52.6%Not measuredOnly Gemma 4 31B measured
MortgageTax (Vals AI)61.4%66.2%Qwen3.7 Plus
SimpleQA Verified10.4%Not measuredOnly Gemma 4 31B measured
LMArena Text: science14571464Qwen3.7 Plus
LMArena Text: medicine and healthcare14511464Qwen3.7 Plus
LMArena Text: legal and government14381451Qwen3.7 Plus
LMArena Text: business and finance14301435Qwen3.7 Plus
FACTS Benchmark Suite45.3%Not measuredOnly Gemma 4 31B measured
Neither model has a result on the other 10 boards here
Web designDirectional onlyPublic boards, shown as published, kept out of the index9 boards, none shared
Web design benchmarks for Gemma 4 31B and Qwen3.7 Plus
BenchmarkGemma 4 31BQwen3.7 PlusLeader
Design Arena: websitesNot measured1269Only Qwen3.7 Plus measured
Design Arena: UI componentsNot measured1261Only Qwen3.7 Plus measured
Design Arena: game devNot measured1262Only Qwen3.7 Plus measured
Design Arena: data vizNot measured1276Only Qwen3.7 Plus measured
Design Arena: 3DNot measured1239Only Qwen3.7 Plus measured
Design Arena: all code categoriesNot measured1269Only Qwen3.7 Plus measured
Design Arena: SVGNot measured1208Only Qwen3.7 Plus measured
Design Arena: ASCII artNot measured1143Only Qwen3.7 Plus measured
LiveBench design58.4%Not measuredOnly Gemma 4 31B measured
GeneralLike-for-likePublic boards, shown as published, kept out of the index521
General benchmarks for Gemma 4 31B and Qwen3.7 Plus
BenchmarkGemma 4 31BQwen3.7 PlusLeader
LiveBench data analysis53.3%Not measuredOnly Gemma 4 31B measured
SAGE (Vals AI)55.0%39.3%Gemma 4 31B
Vals Multimodal IndexNot measured53.9%Only Qwen3.7 Plus measured
IFBench75.6%78.0%Qwen3.7 Plus
Long context reasoning (AA-LCR)69.7%73.0%Qwen3.7 Plus
DTBench82.7%84.0%Qwen3.7 Plus
LMCA39.3%37.6%Gemma 4 31B
Surface Evolver Bench30.6%Not measuredOnly Gemma 4 31B measured
LMArena Text14431454Qwen3.7 Plus
LMArena Text: instruction following14331439Qwen3.7 Plus
LMArena Text: creative writing14171438Qwen3.7 Plus
LMArena Vision12761278Qwen3.7 Plus
LMArena Text: English14511458Qwen3.7 Plus
LMArena Text: non-English14301445Qwen3.7 Plus
LMArena Text: Chinese14751509Qwen3.7 Plus
LMArena Text: GermanNot measured1471Only Qwen3.7 Plus measured
LMArena Text: JapaneseNot measured1412Only Qwen3.7 Plus measured
LMArena Text: KoreanNot measured1413Only Qwen3.7 Plus measured
LMArena Text: French14361472Qwen3.7 Plus
LMArena Text: Spanish14421457Qwen3.7 Plus
LMArena Text: Russian14601457Gemma 4 31B
LMArena Text: Polish14331449Qwen3.7 Plus
LMArena Text: multi-turn14521459Qwen3.7 Plus
LMArena Text: longer queries14461454Qwen3.7 Plus
LMArena Text: writing and language14321437Qwen3.7 Plus
LMArena Text: entertainment and media14051422Qwen3.7 Plus
LMArena Vision: English12711280Qwen3.7 Plus
LMArena Vision: Chinese13261332Qwen3.7 Plus
LMArena Vision: reading text12821288Qwen3.7 Plus
LMArena Vision: humor12801261Gemma 4 31B
LMArena Vision: captioning1218Not measuredOnly Gemma 4 31B measured
LMArena Vision: recognizing things1226Not measuredOnly Gemma 4 31B measured
LMArena Vision: creative writing12851258Gemma 4 31B
LMArena Document14251444Qwen3.7 Plus
Neither model has a result on the other 12 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for Gemma 4 31B and Qwen3.7 Plus
BenchmarkGemma 4 31BQwen3.7 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

Gemma 4 31B$0.0003Fits in one request
Qwen3.7 Plus$0.0010Fits in one request

Gemma 4 31B costs less

Repository review

50K input + 3K output tokens

Gemma 4 31B$0.0082Fits in one request
Qwen3.7 Plus$0.020Fits in one request

Gemma 4 31B costs less

Agent loop

200K input + 10K output tokens

Gemma 4 31B$0.032Fits in one request
Qwen3.7 Plus$0.077Fits in one request

Gemma 4 31B 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 Gemma 4 31B and Qwen3.7 Plus
SpecificationGoogle Gemma 4 31BQwen3.7 Plus
MakerGoogleQwen
WeightsOpen weightsNo public weights listed
ReleasedApril 2, 2026June 3, 2026
Context window262K1M
Input $/Mtok$0.14$0.32
Output $/Mtok$0.40$1.28
Coding index39.033.2
Independent measurements behind it22
Cost per solved taskNot computableNot computable
SourceOpenRouter listingOpenRouter listing

Questions

Is Gemma 4 31B better than Qwen3.7 Plus for coding?

Pick Gemma 4 31B for coding: it scores 39.0 on the Vibe Coding Index against 33.2 for Qwen3.7 Plus. Pick Qwen3.7 Plus for a larger context window (1M against 262K tokens) and work measured by AA Coding Index or SciCode, where it leads.

Which is cheaper, Gemma 4 31B or Qwen3.7 Plus?

Gemma 4 31B costs $0.14 per million input tokens and $0.40 per million output tokens; Qwen3.7 Plus costs $0.32 and $1.28. Cost per solved task is known for neither of them.

Which has the bigger context window, Gemma 4 31B or Qwen3.7 Plus?

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

How many benchmarks is the Gemma 4 31B vs Qwen3.7 Plus comparison based on?

51 benchmarks have a result for both models as of October 21, 2026. Gemma 4 31B's coding index rests on 2 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/gemma-4-31b-it-vs-qwen3-7-plus" title="Gemma 4 31B 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/gemma-4-31b-it-vs-qwen3-7-plus">LLMBenchmark.ai, Gemma 4 31B vs Qwen3.7 Plus</a></p>