LLMBenchmark.ai

Enter opens the highlighted result. Esc closes.

Gemma 4 31B vs MiniMax M3

Updated October 21, 2026. 64 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.

Replace Gemma 4 31B Replace MiniMax M3
Gemma 4 31BGoogle
Coding
38.3
Overall
14.7
Output $/M
$0.40
36
MiniMax M3MiniMax
Coding
57.8
Overall
29.2
Output $/M
$1.20
28
vs boards won of 64 shared

Decision reading

Pick MiniMax M3 for coding: it scores 57.8 on the Vibe Coding Index against 38.3 for Gemma 4 31B.

Pick Gemma 4 31B when output tokens cost 3.0x less, or when what matters is ALE-Bench or LiveBench long agentic, where it leads.

Model AGemma 4 31BGoogle38.3/1002 independent benchmarksNo cost per solved taskModel BMiniMax M3MiniMax57.8/1002 independent benchmarks$0.56 per solved task
Shared results
64
Gemma 4 31B only
4
MiniMax M3 only
52
Like-for-like categories
8 of 9

Shared results can support a head-to-head reading. Results only one model has describe coverage, not superiority.

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 38.3 from 2 benchmarks, MiniMax M3 57.8 from 2 benchmarks.
Widest category
Agentic work, 15.4 points apart on average over 5 shared benchmarks.
Widest single gap
AA Agentic Index: Gemma 4 31B 4.2 against MiniMax M3 29.5, 25.3 points apart on a 0 to 100 scale.
Output price
Gemma 4 31B $0.40 against MiniMax M3 $1.20 per million output tokens, 3.0x apart.
Context window
Gemma 4 31B takes 262K tokens, MiniMax M3 1.05M.

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 31BBarsMiniMax M3Ties
Coding19
Intelligence02
Agentic work14
Reasoning54
Math30
Knowledge32
Web design01
General236
All shared boards3628
CodingLike-for-likeFour of these boards feed the Vibe Coding Index19
Coding benchmarks for Gemma 4 31B and MiniMax M3
BenchmarkGemma 4 31BMiniMax M3Leader
LiveBench coding49.0%70.9%MiniMax M3
LMArena WebDev13671482MiniMax M3
AA Coding Index43.458.6MiniMax M3
LiveCodeBench (Vals AI)Not measured82.2%Only MiniMax M3 measured
SWE-bench Verified (Vals AI)Not measured75.0%Only MiniMax M3 measured
Terminal-Bench 4 (Vals AI)Not measured1.0%Only MiniMax M3 measured
Vibe Code Bench (Vals AI)Not measured47.6%Only MiniMax M3 measured
Code migration (Vals AI)Not measured19.9%Only MiniMax M3 measured
Terminal-Bench 2.1 (Vals AI)Not measured53.6%Only MiniMax M3 measured
SWE-bench Multimodal (Vals AI)Not measured33.3%Only MiniMax M3 measured
Vibe Code Bench 1-100 (Vals AI)Not measured9.2%Only MiniMax M3 measured
SkillsBench (Vals AI)Not measured51.5%Only MiniMax M3 measured
CyberBench (Vals AI)Not measured65.0%Only MiniMax M3 measured
SciCode45.5%47.1%MiniMax M3
Terminal-Bench Hard (Artificial Analysis run)36.4%42.4%MiniMax M3
FrontierCodeNot measured14.7%Only MiniMax M3 measured
WeirdML52.3%Not measuredOnly Gemma 4 31B measured
ALE-Bench925.5640.0Gemma 4 31B
LMArena Text: coding14591470MiniMax M3
LMArena Text: software and IT14631466MiniMax M3
LMArena WebDev: React13591478MiniMax M3
LMArena WebDev: HTML13801455MiniMax M3
LMArena WebDev: from an imageNot measured1470Only MiniMax M3 measured
Neither model has a result on the other 15 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index02
Intelligence benchmarks for Gemma 4 31B and MiniMax M3
BenchmarkGemma 4 31BMiniMax M3Leader
AA Intelligence Index14.729.2MiniMax M3
Epoch Capabilities Index143.0146.9MiniMax M3
Agentic workLike-for-likePublic boards, shown as published, kept out of the index14
Agentic work benchmarks for Gemma 4 31B and MiniMax M3
BenchmarkGemma 4 31BMiniMax M3Leader
AA Agentic Index4.229.5MiniMax M3
Design Arena: agents building web appsNot measured1200Only MiniMax M3 measured
Design Arena: agents building full-stack appsNot measured1197Only MiniMax M3 measured
Design Arena: agents building mobile appsNot measured1169Only MiniMax M3 measured
Design Arena: agents building Android appsNot measured1164Only MiniMax M3 measured
Design Arena: agents building gamesNot measured1158Only MiniMax M3 measured
Design Arena: HTML slidesNot measured1180Only MiniMax M3 measured
Design Arena: PowerPoint slidesNot measured1205Only MiniMax M3 measured
Design Arena: spreadsheetsNot measured1021Only MiniMax M3 measured
LiveBench research44.4%68.0%MiniMax M3
LiveBench browser4.0%8.0%MiniMax M3
LiveBench long agentic13.3%12.4%Gemma 4 31B
Finance Agent (Vals AI)Not measured48.3%Only MiniMax M3 measured
Tax Agent Bench (Vals AI)Not measured20.6%Only MiniMax M3 measured
Legal Research Bench (Vals AI)Not measured29.8%Only MiniMax M3 measured
Excel Modeling Benchmark (Vals AI)Not measured47.8%Only MiniMax M3 measured
τ²-Bench Telecom65.5%88.9%MiniMax M3
APEX-AgentsNot measured37.7%Only MiniMax M3 measured
OSWorld 2.0Not measured4.6%Only MiniMax M3 measured
Vending-Bench 2Not measured$2,158Only MiniMax M3 measured
Neither model has a result on the other 19 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index54
Reasoning benchmarks for Gemma 4 31B and MiniMax M3
BenchmarkGemma 4 31BMiniMax M3Leader
GPQA DiamondNot measured92.7%Only MiniMax M3 measured
LiveBench reasoning68.3%74.5%MiniMax M3
MMMU Pro (Vals AI)Not measured81.2%Only MiniMax M3 measured
GPQA Diamond (Artificial Analysis run)85.7%92.9%MiniMax M3
Humanity's Last Exam (Artificial Analysis run)23.6%39.0%MiniMax M3
GPQA Diamond (Epoch AI run)75.8%90.9%MiniMax M3
SimpleBenchNot measured45.8%Only MiniMax M3 measured
Chess puzzlesNot measured13.0%Only MiniMax M3 measured
Mystery game puzzlesNot measured8.0%Only MiniMax M3 measured
LMArena Text: hard prompts14481447Gemma 4 31B
LMArena Text: expert14641461Gemma 4 31B
LMArena Text: hard prompts in English14561455Gemma 4 31B
LMArena Vision: diagrams12831266Gemma 4 31B
LMArena Vision: homework13101268Gemma 4 31B
Neither model has a result on the other 7 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index30
Math benchmarks for Gemma 4 31B and MiniMax M3
BenchmarkGemma 4 31BMiniMax M3Leader
OTIS Mock AIME73.3%71.1%Gemma 4 31B
ProofBenchNot measured18.0%Only MiniMax M3 measured
LMArena Text: math14631429Gemma 4 31B
LMArena Text: mathematical work14651448Gemma 4 31B
Neither model has a result on the other 9 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index32
Knowledge benchmarks for Gemma 4 31B and MiniMax M3
BenchmarkGemma 4 31BMiniMax M3Leader
MMLU ProNot measured84.2%Only MiniMax M3 measured
LegalBench (Vals AI)Not measured85.4%Only MiniMax M3 measured
CaseLaw (Vals AI)52.6%Not measuredOnly Gemma 4 31B measured
CorpFin (Vals AI)Not measured68.1%Only MiniMax M3 measured
TaxEval (Vals AI)Not measured72.7%Only MiniMax M3 measured
MortgageTax (Vals AI)61.4%68.4%MiniMax M3
MedCode (Vals AI)Not measured46.3%Only MiniMax M3 measured
SimpleQA Verified10.4%Not measuredOnly Gemma 4 31B measured
LMArena Text: science14571452Gemma 4 31B
LMArena Text: medicine and healthcare14511441Gemma 4 31B
LMArena Text: legal and government14381437Gemma 4 31B
LMArena Text: business and finance14301434MiniMax M3
Neither model has a result on the other 5 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index01
Web design benchmarks for Gemma 4 31B and MiniMax M3
BenchmarkGemma 4 31BMiniMax M3Leader
Design Arena: websitesNot measured1257Only MiniMax M3 measured
Design Arena: UI componentsNot measured1246Only MiniMax M3 measured
Design Arena: game devNot measured1210Only MiniMax M3 measured
Design Arena: data vizNot measured1235Only MiniMax M3 measured
Design Arena: 3DNot measured1209Only MiniMax M3 measured
Design Arena: all code categoriesNot measured1247Only MiniMax M3 measured
Design Arena: SVGNot measured1161Only MiniMax M3 measured
Design Arena: ASCII artNot measured1161Only MiniMax M3 measured
LiveBench design58.4%66.2%MiniMax M3
GeneralLike-for-likePublic boards, shown as published, kept out of the index236
General benchmarks for Gemma 4 31B and MiniMax M3
BenchmarkGemma 4 31BMiniMax M3Leader
LiveBench data analysis53.3%76.2%MiniMax M3
Public Benefits Bench (Vals AI)Not measured64.1%Only MiniMax M3 measured
SAGE (Vals AI)55.0%50.6%Gemma 4 31B
MedScribe (Vals AI)Not measured87.3%Only MiniMax M3 measured
Vals Multimodal IndexNot measured60.0%Only MiniMax M3 measured
IFBench75.6%82.9%MiniMax M3
Long context reasoning (AA-LCR)69.7%83.0%MiniMax M3
DTBench82.7%78.9%Gemma 4 31B
LMCA39.3%33.7%Gemma 4 31B
Surface Evolver Bench30.6%55.0%MiniMax M3
LMArena Text14431433Gemma 4 31B
LMArena Text: instruction following14331433Gemma 4 31B
LMArena Text: creative writing14171404Gemma 4 31B
LMArena Vision12761251Gemma 4 31B
LMArena Text: English14511443Gemma 4 31B
LMArena Text: non-English14301420Gemma 4 31B
LMArena Text: Chinese14751466Gemma 4 31B
LMArena Text: GermanNot measured1428Only MiniMax M3 measured
LMArena Text: JapaneseNot measured1380Only MiniMax M3 measured
LMArena Text: KoreanNot measured1373Only MiniMax M3 measured
LMArena Text: French14361444MiniMax M3
LMArena Text: Spanish14421433Gemma 4 31B
LMArena Text: Russian14601426Gemma 4 31B
LMArena Text: Polish14331423Gemma 4 31B
LMArena Text: multi-turn14521443Gemma 4 31B
LMArena Text: longer queries14461446Gemma 4 31B
LMArena Text: writing and language14321419Gemma 4 31B
LMArena Text: entertainment and media14051403Gemma 4 31B
LMArena Vision: English12711263Gemma 4 31B
LMArena Vision: Chinese13261311Gemma 4 31B
LMArena Vision: reading text12821259Gemma 4 31B
LMArena Vision: humor12801235Gemma 4 31B
LMArena Vision: captioning1218Not measuredOnly Gemma 4 31B measured
LMArena Vision: recognizing things12261197Gemma 4 31B
LMArena Vision: creative writing12851234Gemma 4 31B
LMArena Document14251435MiniMax M3
Neither model has a result on the other 10 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 MiniMax M3
BenchmarkGemma 4 31BMiniMax M3Leader
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$0.0004Fits in one request
MiniMax M3$0.0009Fits in one request

Gemma 4 31B costs less

Repository review

50K input + 3K output tokens

Gemma 4 31B$0.011Fits in one request
MiniMax M3$0.019Fits in one request

Gemma 4 31B costs less

Agent loop

200K input + 10K output tokens

Gemma 4 31B$0.044Fits in one request
MiniMax M3$0.072Fits 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 MiniMax M3
SpecificationGoogle Gemma 4 31BMiniMax M3
MakerGoogleMiniMax
WeightsOpen weightsOpen weights
ReleasedApril 2, 2026May 31, 2026
Context window262K1.05M
Input $/Mtok$0.20$0.30
Output $/Mtok$0.40$1.20
Coding index38.357.8
Independent measurements behind it22
Cost per solved taskNot computable$0.56
SourceOpenRouter listingOpenRouter listing

Questions

Is Gemma 4 31B better than MiniMax M3 for coding?

Pick MiniMax M3 for coding: it scores 57.8 on the Vibe Coding Index against 38.3 for Gemma 4 31B. Pick Gemma 4 31B when output tokens cost 3.0x less, or when what matters is ALE-Bench or LiveBench long agentic, where it leads.

Which is cheaper, Gemma 4 31B or MiniMax M3?

Gemma 4 31B costs $0.20 per million input tokens and $0.40 per million output tokens; MiniMax M3 costs $0.30 and $1.20. Cost per solved task is known for MiniMax M3 only.

Which has the bigger context window, Gemma 4 31B or MiniMax M3?

MiniMax M3, with 1.05M tokens against 262K.

How many benchmarks is the Gemma 4 31B vs MiniMax M3 comparison based on?

64 benchmarks have a result for both models as of October 21, 2026. Gemma 4 31B's coding index rests on 2 independent benchmarks and MiniMax M3'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-minimax-minimax-m3" title="Gemma 4 31B vs MiniMax M3, 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-minimax-minimax-m3">LLMBenchmark.ai, Gemma 4 31B vs MiniMax M3</a></p>