Enter opens the highlighted result. Esc closes.

MiniMax M2.7 vs MiniMax M3

MiniMax M3 leads MiniMax M2.7 on coding, 39.2 to 36.2 on the Vibe Coding Index, at about the same output price ($1.20 vs $1.20 per million). Updated October 22, 2026; 68 benchmarks have a result for both.

Replace MiniMax M2.7 Replace MiniMax M3
MiniMax M2.7MiniMax
Coding
36.2
Overall
44.5
Output $/M
$1.20
1
MiniMax M3MiniMax
Coding
39.2
Overall
51.7
Output $/M
$1.20
67
vs boards won of 68 shared

MiniMax M2.7 or MiniMax M3: which to pick

Pick MiniMax M3 for coding: it scores 39.2 on the Vibe Coding Index against 36.2 for MiniMax M2.7.

Pick MiniMax M2.7 for work measured by SciCode, where it leads.

Model AMiniMax M2.7MiniMax36.2/1003 independent benchmarks$0.64 per solved taskModel BMiniMax M3MiniMax39.2/1006 independent benchmarks$0.56 per solved task
Shared results
68
MiniMax M2.7 only
6
MiniMax M3 only
49
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
MiniMax M2.7 36.2 from 3 benchmarks, MiniMax M3 39.2 from 6 benchmarks.
Widest category
Agentic work, 15.2 points apart on average over 6 shared benchmarks.
Widest single gap
Vibe Code Bench (Vals AI): MiniMax M2.7 11.9% against MiniMax M3 47.6%, 35.6 points apart on a 0 to 100 scale.
Output price
Both cost $1.20 per million output tokens.
Context window
MiniMax M2.7 takes 205K 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
CategoryMiniMax M2.7BarsMiniMax M3Ties
Coding113
Intelligence02
Agentic work06
Reasoning06
Math03
Knowledge09
Web design08
General020
All shared boards167
CodingLike-for-likeSix of these boards feed the Vibe Coding Index113
Coding benchmarks for MiniMax M2.7 and MiniMax M3
BenchmarkMiniMax M2.7MiniMax M3Leader
LiveBench codingNot measured70.9%Only MiniMax M3 measured
LMArena WebDev13991482MiniMax M3
AA Coding Index52.658.6MiniMax M3
LiveCodeBench (Vals AI)79.9%82.2%MiniMax M3
SWE-bench Verified (Vals AI)73.8%75.0%MiniMax M3
Terminal-Bench 4 (Vals AI)Not measured1.0%Only MiniMax M3 measured
Vibe Code Bench (Vals AI)11.9%47.6%MiniMax M3
Code migration (Vals AI)8.7%19.9%MiniMax M3
ProgramBench (Vals AI)0.0%Not measuredOnly MiniMax M2.7 measured
Terminal-Bench 2.1 (Vals AI)48.7%53.6%MiniMax M3
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
SciCode50.1%47.1%MiniMax M2.7
Terminal-Bench Hard (Artificial Analysis run)39.4%42.4%MiniMax M3
Terminal-Bench45.1%Not measuredOnly MiniMax M2.7 measured
FrontierCodeNot measured14.7%Only MiniMax M3 measured
WeirdML37.0%Not measuredOnly MiniMax M2.7 measured
ALE-Bench599.3640.0MiniMax M3
LMArena Text: coding14541470MiniMax M3
LMArena Text: software and IT14461466MiniMax M3
LMArena WebDev: React13881478MiniMax M3
LMArena WebDev: HTML14011455MiniMax M3
LMArena WebDev: from an imageNot measured1470Only MiniMax M3 measured
Neither model has a result on the other 18 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index02
Intelligence benchmarks for MiniMax M2.7 and MiniMax M3
BenchmarkMiniMax M2.7MiniMax M3Leader
AA Intelligence Index22.829.2MiniMax M3
Epoch Capabilities Index145.8146.9MiniMax M3
Agentic workLike-for-likePublic boards, shown as published, kept out of the index06
Agentic work benchmarks for MiniMax M2.7 and MiniMax M3
BenchmarkMiniMax M2.7MiniMax M3Leader
AA Agentic Index15.329.5MiniMax 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 measured1158Only MiniMax M3 measured
Design Arena: agents building gamesNot measured1159Only MiniMax M3 measured
Design Arena: HTML slidesNot measured1120Only MiniMax M3 measured
Design Arena: PowerPoint slidesNot measured1178Only MiniMax M3 measured
Design Arena: spreadsheetsNot measured1042Only MiniMax M3 measured
LiveBench researchNot measured68.0%Only MiniMax M3 measured
LiveBench browserNot measured8.0%Only MiniMax M3 measured
LiveBench long agenticNot measured12.4%Only MiniMax M3 measured
Finance Agent (Vals AI)27.9%48.3%MiniMax M3
Tax Agent Bench (Vals AI)6.9%20.6%MiniMax M3
Legal Research Bench (Vals AI)10.6%29.8%MiniMax M3
Excel Modeling Benchmark (Vals AI)28.4%47.8%MiniMax M3
τ²-Bench Telecom84.8%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 22 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index06
Reasoning benchmarks for MiniMax M2.7 and MiniMax M3
BenchmarkMiniMax M2.7MiniMax M3Leader
GPQA Diamond86.6%92.7%MiniMax M3
LiveBench reasoningNot measured74.5%Only MiniMax M3 measured
MMMU Pro (Vals AI)Not measured81.2%Only MiniMax M3 measured
GPQA Diamond (Artificial Analysis run)87.4%92.9%MiniMax M3
Humanity's Last Exam (Artificial Analysis run)29.6%39.0%MiniMax M3
GPQA Diamond (Epoch AI run)Not measured90.9%Only MiniMax M3 measured
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 prompts14221447MiniMax M3
LMArena Text: expert14431461MiniMax M3
LMArena Text: hard prompts in English14411455MiniMax M3
LMArena Vision: diagramsNot measured1266Only MiniMax M3 measured
LMArena Vision: homeworkNot measured1268Only MiniMax M3 measured
Neither model has a result on the other 9 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index03
Math benchmarks for MiniMax M2.7 and MiniMax M3
BenchmarkMiniMax M2.7MiniMax M3Leader
AIME91.0%Not measuredOnly MiniMax M2.7 measured
OTIS Mock AIMENot measured71.1%Only MiniMax M3 measured
ProofBench3.0%18.0%MiniMax M3
LMArena Text: math14211429MiniMax M3
LMArena Text: mathematical work14371448MiniMax M3
Neither model has a result on the other 9 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index09
Knowledge benchmarks for MiniMax M2.7 and MiniMax M3
BenchmarkMiniMax M2.7MiniMax M3Leader
MMLU Pro80.4%84.2%MiniMax M3
LegalBench (Vals AI)84.0%85.4%MiniMax M3
CaseLaw (Vals AI)60.9%Not measuredOnly MiniMax M2.7 measured
CorpFin (Vals AI)61.2%68.1%MiniMax M3
TaxEval (Vals AI)66.6%72.7%MiniMax M3
MortgageTax (Vals AI)Not measured68.4%Only MiniMax M3 measured
MedCode (Vals AI)34.4%46.3%MiniMax M3
LMArena Text: science14161452MiniMax M3
LMArena Text: medicine and healthcare14091441MiniMax M3
LMArena Text: legal and government14031437MiniMax M3
LMArena Text: business and finance14071434MiniMax M3
Neither model has a result on the other 9 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index08
Web design benchmarks for MiniMax M2.7 and MiniMax M3
BenchmarkMiniMax M2.7MiniMax M3Leader
Design Arena: websites12421257MiniMax M3
Design Arena: UI components12071243MiniMax M3
Design Arena: game dev12091210MiniMax M3
Design Arena: data viz12331236MiniMax M3
Design Arena: 3D11941208MiniMax M3
Design Arena: all code categories12331246MiniMax M3
Design Arena: SVG11371160MiniMax M3
Design Arena: ASCII art11361161MiniMax M3
LiveBench designNot measured66.2%Only MiniMax M3 measured
GeneralLike-for-likePublic boards, shown as published, kept out of the index020
General benchmarks for MiniMax M2.7 and MiniMax M3
BenchmarkMiniMax M2.7MiniMax M3Leader
LiveBench data analysisNot measured76.2%Only MiniMax M3 measured
Public Benefits Bench (Vals AI)Not measured64.1%Only MiniMax M3 measured
SAGE (Vals AI)Not measured50.6%Only MiniMax M3 measured
MedScribe (Vals AI)79.9%87.3%MiniMax M3
Vals Multimodal IndexNot measured60.0%Only MiniMax M3 measured
IFBench75.7%82.9%MiniMax M3
Long context reasoning (AA-LCR)78.3%83.0%MiniMax M3
DTBenchNot measured78.9%Only MiniMax M3 measured
LMCANot measured33.7%Only MiniMax M3 measured
Surface Evolver BenchNot measured55.0%Only MiniMax M3 measured
ExploitBench13.3%Not measuredOnly MiniMax M2.7 measured
LMArena Text14051433MiniMax M3
LMArena Text: instruction following14051433MiniMax M3
LMArena Text: creative writing13541404MiniMax M3
LMArena VisionNot measured1251Only MiniMax M3 measured
LMArena Text: English14261443MiniMax M3
LMArena Text: non-English13821420MiniMax M3
LMArena Text: Chinese14421466MiniMax M3
LMArena Text: German13981428MiniMax M3
LMArena Text: Japanese12601380MiniMax M3
LMArena Text: Korean13141373MiniMax M3
LMArena Text: French14241444MiniMax M3
LMArena Text: Spanish14021433MiniMax M3
LMArena Text: Russian13831426MiniMax M3
LMArena Text: Polish13871423MiniMax M3
LMArena Text: multi-turn14121443MiniMax M3
LMArena Text: longer queries14181446MiniMax M3
LMArena Text: writing and language13761419MiniMax M3
LMArena Text: entertainment and media13601403MiniMax M3
LMArena Vision: EnglishNot measured1263Only MiniMax M3 measured
LMArena Vision: ChineseNot measured1311Only MiniMax M3 measured
LMArena Vision: reading textNot measured1259Only MiniMax M3 measured
LMArena Vision: humorNot measured1235Only MiniMax M3 measured
LMArena Vision: recognizing thingsNot measured1197Only MiniMax M3 measured
LMArena Vision: creative writingNot measured1234Only MiniMax M3 measured
LMArena DocumentNot measured1435Only MiniMax M3 measured
EQ-Bench 4Not measured1150Only MiniMax M3 measured
Neither model has a result on the other 11 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for MiniMax M2.7 and MiniMax M3
BenchmarkMiniMax M2.7MiniMax 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

MiniMax M2.7$0.0009Fits in one request
MiniMax M3$0.0009Fits in one request

Same cost

Repository review

50K input + 3K output tokens

MiniMax M2.7$0.019Fits in one request
MiniMax M3$0.019Fits in one request

Same cost

Agent loop

200K input + 10K output tokens

MiniMax M2.7$0.072Exceeds the context window
MiniMax M3$0.072Fits in one request

Same cost

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 MiniMax M2.7 and MiniMax M3
SpecificationMiniMax M2.7MiniMax M3
MakerMiniMaxMiniMax
WeightsOpen weightsOpen weights
ReleasedMarch 18, 2026May 31, 2026
Context window205K1.05M
Input $/Mtok$0.30$0.30
Output $/Mtok$1.20$1.20
Coding index36.239.2
Independent measurements behind it36
Cost per solved task$0.64$0.56
SourceOpenRouter listingOpenRouter listing

Questions

Is MiniMax M2.7 better than MiniMax M3 for coding?

Pick MiniMax M3 for coding: it scores 39.2 on the Vibe Coding Index against 36.2 for MiniMax M2.7. Pick MiniMax M2.7 for work measured by SciCode, where it leads.

Which is cheaper, MiniMax M2.7 or MiniMax M3?

MiniMax M2.7 costs $0.30 per million input tokens and $1.20 per million output tokens; MiniMax M3 costs $0.30 and $1.20. Per solved SWE-bench Verified task, MiniMax M2.7 costs $0.64 and MiniMax M3 $0.56.

Which has the bigger context window, MiniMax M2.7 or MiniMax M3?

MiniMax M3, with 1.05M tokens against 205K.

How many benchmarks is the MiniMax M2.7 vs MiniMax M3 comparison based on?

68 benchmarks have a result for both models as of October 22, 2026. MiniMax M2.7's coding index rests on 3 independent benchmarks and MiniMax M3's on 6. 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/minimax-minimax-m2-7-vs-minimax-minimax-m3" title="MiniMax M2.7 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/minimax-minimax-m2-7-vs-minimax-minimax-m3">LLMBenchmark.ai, MiniMax M2.7 vs MiniMax M3</a></p>