Enter opens the highlighted result. Esc closes.

MiniMax M3 vs MiMo-V2.6-Flash

MiMo-V2.6-Flash leads MiniMax M3 on coding, 54.7 to 39.2 on the Vibe Coding Index, and MiMo-V2.6-Flash costs 4.3x less per output token ($0.28 vs $1.20 per million). Updated October 22, 2026; 57 benchmarks have a result for both.

Replace MiniMax M3 Replace MiMo-V2.6-Flash
MiniMax M3MiniMax
Coding
39.2
Overall
51.7
Output $/M
$1.20
10
MiMo-V2.6-FlashXiaomi
Coding
54.7
Overall
60.8
Output $/M
$0.28
47
vs boards won of 57 shared

MiniMax M3 or MiMo-V2.6-Flash: which to pick

Pick MiMo-V2.6-Flash for coding: it scores 54.7 on the Vibe Coding Index against 39.2 for MiniMax M3, though on 3 benchmarks against 6.

Pick MiniMax M3 for work measured by Humanity's Last Exam (Artificial Analysis run) or MedCode (Vals AI), where it leads.

Model AMiniMax M3MiniMax39.2/1006 independent benchmarks$0.56 per solved taskModel BMiMo-V2.6-FlashXiaomi54.7/1003 independent benchmarksNo cost per solved task
Shared results
57
MiniMax M3 only
60
MiMo-V2.6-Flash only
9
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
MiniMax M3 39.2 from 6 benchmarks, MiMo-V2.6-Flash 54.7 from 3 benchmarks.
Widest category
Math, 19.3 points apart on average over 3 shared benchmarks.
Widest single gap
ProofBench: MiniMax M3 18.0% against MiMo-V2.6-Flash 63.0%, 45.0 points apart on a 0 to 100 scale.
Output price
MiniMax M3 $1.20 against MiMo-V2.6-Flash $0.28 per million output tokens, 4.3x apart.
Context window
MiniMax M3 takes 1.05M tokens, MiMo-V2.6-Flash 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 M3BarsMiMo-V2.6-FlashTies
Coding013
Intelligence01
Agentic work04
Reasoning15
Math03
Knowledge23
General718
All shared boards1047
CodingLike-for-likeSix of these boards feed the Vibe Coding Index013
Coding benchmarks for MiniMax M3 and MiMo-V2.6-Flash
BenchmarkMiniMax M3MiMo-V2.6-FlashLeader
LiveBench coding70.9%Not measuredOnly MiniMax M3 measured
LMArena WebDev14821634MiMo-V2.6-Flash
AA Coding Index58.6Not measuredOnly MiniMax M3 measured
LiveCodeBench (Vals AI)82.2%Not measuredOnly MiniMax M3 measured
SWE-bench Verified (Vals AI)75.0%Not measuredOnly MiniMax M3 measured
Terminal-Bench 4 (Vals AI)1.0%24.2%MiMo-V2.6-Flash
Vibe Code Bench (Vals AI)47.6%79.0%MiMo-V2.6-Flash
Code migration (Vals AI)19.9%40.9%MiMo-V2.6-Flash
ProgramBench (Vals AI)Not measured0.5%Only MiMo-V2.6-Flash measured
IOI (Vals AI)Not measured47.7%Only MiMo-V2.6-Flash measured
Terminal-Bench 2.1 (Vals AI)53.6%76.4%MiMo-V2.6-Flash
SWE-bench Multimodal (Vals AI)33.3%Not measuredOnly MiniMax M3 measured
Vibe Code Bench 1-100 (Vals AI)9.2%Not measuredOnly MiniMax M3 measured
SkillsBench (Vals AI)51.5%Not measuredOnly MiniMax M3 measured
CyberBench (Vals AI)65.0%75.4%MiMo-V2.6-Flash
SciCode47.1%51.3%MiMo-V2.6-Flash
Terminal-Bench Hard (Artificial Analysis run)42.4%Not measuredOnly MiniMax M3 measured
FrontierCode14.7%Not measuredOnly MiniMax M3 measured
ALE-Bench640.01244.2MiMo-V2.6-Flash
LMArena Text: coding14701499MiMo-V2.6-Flash
LMArena Text: software and IT14661497MiMo-V2.6-Flash
LMArena WebDev: React14781648MiMo-V2.6-Flash
LMArena WebDev: HTML14551641MiMo-V2.6-Flash
LMArena WebDev: from an image14701596MiMo-V2.6-Flash
Neither model has a result on the other 19 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index01
Intelligence benchmarks for MiniMax M3 and MiMo-V2.6-Flash
BenchmarkMiniMax M3MiMo-V2.6-FlashLeader
AA Intelligence Index29.237.9MiMo-V2.6-Flash
Epoch Capabilities Index146.9Not measuredOnly MiniMax M3 measured
Agentic workLike-for-likePublic boards, shown as published, kept out of the index04
Agentic work benchmarks for MiniMax M3 and MiMo-V2.6-Flash
BenchmarkMiniMax M3MiMo-V2.6-FlashLeader
AA Agentic Index29.5Not measuredOnly MiniMax M3 measured
Design Arena: agents building web apps1200Not measuredOnly MiniMax M3 measured
Design Arena: agents building full-stack apps1197Not measuredOnly MiniMax M3 measured
Design Arena: agents building mobile apps1169Not measuredOnly MiniMax M3 measured
Design Arena: agents building Android apps1158Not measuredOnly MiniMax M3 measured
Design Arena: agents building games1159Not measuredOnly MiniMax M3 measured
Design Arena: HTML slides1120Not measuredOnly MiniMax M3 measured
Design Arena: PowerPoint slides1178Not measuredOnly MiniMax M3 measured
Design Arena: spreadsheets1042Not measuredOnly MiniMax M3 measured
LiveBench research68.0%Not measuredOnly MiniMax M3 measured
LiveBench browser8.0%Not measuredOnly MiniMax M3 measured
LiveBench long agentic12.4%Not measuredOnly MiniMax M3 measured
SREBench (Vals AI)Not measured4.2%Only MiMo-V2.6-Flash measured
Finance Agent (Vals AI)48.3%56.3%MiMo-V2.6-Flash
Tax Agent Bench (Vals AI)20.6%28.5%MiMo-V2.6-Flash
Legal Research Bench (Vals AI)29.8%38.0%MiMo-V2.6-Flash
Harvey's Legal Agent Benchmark (Vals AI)Not measured13.3%Only MiMo-V2.6-Flash measured
Excel Modeling Benchmark (Vals AI)47.8%65.5%MiMo-V2.6-Flash
BioMysteryBench (Vals AI)Not measured69.3%Only MiMo-V2.6-Flash measured
Terminal-Bench-Science (Vals AI)Not measured4.3%Only MiMo-V2.6-Flash measured
Vals Science IndexNot measured31.7%Only MiMo-V2.6-Flash measured
τ²-Bench Telecom88.9%Not measuredOnly MiniMax M3 measured
APEX-Agents37.7%Not measuredOnly MiniMax M3 measured
OSWorld 2.04.6%Not measuredOnly MiniMax M3 measured
Vending-Bench 2$2,158Not measuredOnly MiniMax M3 measured
Neither model has a result on the other 17 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index15
Reasoning benchmarks for MiniMax M3 and MiMo-V2.6-Flash
BenchmarkMiniMax M3MiMo-V2.6-FlashLeader
GPQA Diamond92.7%Not measuredOnly MiniMax M3 measured
LiveBench reasoning74.5%Not measuredOnly MiniMax M3 measured
MysteryMechanism (Vals AI)Not measured21.6%Only MiMo-V2.6-Flash measured
MMMU Pro (Vals AI)81.2%Not measuredOnly MiniMax M3 measured
GPQA Diamond (Artificial Analysis run)92.9%Not measuredOnly MiniMax M3 measured
Humanity's Last Exam (Artificial Analysis run)39.0%35.1%MiniMax M3
GPQA Diamond (Epoch AI run)90.9%Not measuredOnly MiniMax M3 measured
SimpleBench45.8%Not measuredOnly MiniMax M3 measured
Chess puzzles13.0%Not measuredOnly MiniMax M3 measured
Mystery game puzzles8.0%Not measuredOnly MiniMax M3 measured
LMArena Text: hard prompts14471475MiMo-V2.6-Flash
LMArena Text: expert14611496MiMo-V2.6-Flash
LMArena Text: hard prompts in English14551493MiMo-V2.6-Flash
LMArena Vision: diagrams12661276MiMo-V2.6-Flash
LMArena Vision: homework12681283MiMo-V2.6-Flash
Neither model has a result on the other 8 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index03
Math benchmarks for MiniMax M3 and MiMo-V2.6-Flash
BenchmarkMiniMax M3MiMo-V2.6-FlashLeader
OTIS Mock AIME71.1%Not measuredOnly MiniMax M3 measured
ProofBench18.0%63.0%MiMo-V2.6-Flash
LMArena Text: math14291476MiMo-V2.6-Flash
LMArena Text: mathematical work14481478MiMo-V2.6-Flash
Neither model has a result on the other 10 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index23
Knowledge benchmarks for MiniMax M3 and MiMo-V2.6-Flash
BenchmarkMiniMax M3MiMo-V2.6-FlashLeader
MMLU Pro84.2%Not measuredOnly MiniMax M3 measured
LegalBench (Vals AI)85.4%Not measuredOnly MiniMax M3 measured
CorpFin (Vals AI)68.1%Not measuredOnly MiniMax M3 measured
TaxEval (Vals AI)72.7%Not measuredOnly MiniMax M3 measured
MortgageTax (Vals AI)68.4%Not measuredOnly MiniMax M3 measured
MedCode (Vals AI)46.3%41.1%MiniMax M3
LMArena Text: science14521462MiMo-V2.6-Flash
LMArena Text: medicine and healthcare14411439MiniMax M3
LMArena Text: legal and government14371441MiMo-V2.6-Flash
LMArena Text: business and finance14341454MiMo-V2.6-Flash
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 MiniMax M3 and MiMo-V2.6-Flash
BenchmarkMiniMax M3MiMo-V2.6-FlashLeader
Design Arena: websites1257Not measuredOnly MiniMax M3 measured
Design Arena: UI components1243Not measuredOnly MiniMax M3 measured
Design Arena: game dev1210Not measuredOnly MiniMax M3 measured
Design Arena: data viz1236Not measuredOnly MiniMax M3 measured
Design Arena: 3D1208Not measuredOnly MiniMax M3 measured
Design Arena: all code categories1246Not measuredOnly MiniMax M3 measured
Design Arena: SVG1160Not measuredOnly MiniMax M3 measured
Design Arena: ASCII art1161Not measuredOnly MiniMax M3 measured
LiveBench design66.2%Not measuredOnly MiniMax M3 measured
GeneralLike-for-likePublic boards, shown as published, kept out of the index718
General benchmarks for MiniMax M3 and MiMo-V2.6-Flash
BenchmarkMiniMax M3MiMo-V2.6-FlashLeader
Vals IndexNot measured54.8%Only MiMo-V2.6-Flash measured
LiveBench data analysis76.2%Not measuredOnly MiniMax M3 measured
Public Benefits Bench (Vals AI)64.1%67.6%MiMo-V2.6-Flash
SAGE (Vals AI)50.6%43.5%MiniMax M3
MedScribe (Vals AI)87.3%85.3%MiniMax M3
Vals Multimodal Index60.0%Not measuredOnly MiniMax M3 measured
IFBench82.9%Not measuredOnly MiniMax M3 measured
Long context reasoning (AA-LCR)83.0%74.3%MiniMax M3
DTBench78.9%Not measuredOnly MiniMax M3 measured
LMCA33.7%Not measuredOnly MiniMax M3 measured
Surface Evolver Bench55.0%Not measuredOnly MiniMax M3 measured
LMArena Text14331453MiMo-V2.6-Flash
LMArena Text: instruction following14331452MiMo-V2.6-Flash
LMArena Text: creative writing14041403MiniMax M3
LMArena Vision12511256MiMo-V2.6-Flash
LMArena Text: English14431476MiMo-V2.6-Flash
LMArena Text: non-English14201431MiMo-V2.6-Flash
LMArena Text: Chinese14661509MiMo-V2.6-Flash
LMArena Text: German14281458MiMo-V2.6-Flash
LMArena Text: Japanese13801359MiniMax M3
LMArena Text: Korean13731425MiMo-V2.6-Flash
LMArena Text: French14441480MiMo-V2.6-Flash
LMArena Text: Spanish14331453MiMo-V2.6-Flash
LMArena Text: Russian14261409MiniMax M3
LMArena Text: Polish14231455MiMo-V2.6-Flash
LMArena Text: multi-turn14431447MiMo-V2.6-Flash
LMArena Text: longer queries14461459MiMo-V2.6-Flash
LMArena Text: writing and language14191424MiMo-V2.6-Flash
LMArena Text: entertainment and media14031415MiMo-V2.6-Flash
LMArena Vision: English12631269MiMo-V2.6-Flash
LMArena Vision: Chinese1311Not measuredOnly MiniMax M3 measured
LMArena Vision: reading text12591270MiMo-V2.6-Flash
LMArena Vision: humor1235Not measuredOnly MiniMax M3 measured
LMArena Vision: recognizing things1197Not measuredOnly MiniMax M3 measured
LMArena Vision: creative writing12341231MiniMax M3
LMArena Document1435Not measuredOnly MiniMax M3 measured
EQ-Bench 41150Not measuredOnly 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 M3 and MiMo-V2.6-Flash
BenchmarkMiniMax M3MiMo-V2.6-FlashLeader
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 M3$0.0009Fits in one request
MiMo-V2.6-Flash$0.0003Fits in one request

MiMo-V2.6-Flash costs less

Repository review

50K input + 3K output tokens

MiniMax M3$0.019Fits in one request
MiMo-V2.6-Flash$0.0078Fits in one request

MiMo-V2.6-Flash costs less

Agent loop

200K input + 10K output tokens

MiniMax M3$0.072Fits in one request
MiMo-V2.6-Flash$0.031Fits in one request

MiMo-V2.6-Flash 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 MiniMax M3 and MiMo-V2.6-Flash
SpecificationMiniMax M3Xiaomi MiMo-V2.6-Flash
MakerMiniMaxXiaomi
WeightsOpen weightsOpen weights
ReleasedMay 31, 2026September 21, 2026
Context window1.05M1.05M
Input $/Mtok$0.30$0.14
Output $/Mtok$1.20$0.28
Coding index39.254.7
Independent measurements behind it63
Cost per solved task$0.56Not computable
SourceOpenRouter listingOpenRouter listing

Questions

Is MiniMax M3 better than MiMo-V2.6-Flash for coding?

Pick MiMo-V2.6-Flash for coding: it scores 54.7 on the Vibe Coding Index against 39.2 for MiniMax M3, though on 3 benchmarks against 6. Pick MiniMax M3 for work measured by Humanity's Last Exam (Artificial Analysis run) or MedCode (Vals AI), where it leads.

Which is cheaper, MiniMax M3 or MiMo-V2.6-Flash?

MiniMax M3 costs $0.30 per million input tokens and $1.20 per million output tokens; MiMo-V2.6-Flash costs $0.14 and $0.28. Cost per solved task is known for MiniMax M3 only.

Which has the bigger context window, MiniMax M3 or MiMo-V2.6-Flash?

MiMo-V2.6-Flash, with 1.05M tokens against 1.05M.

How many benchmarks is the MiniMax M3 vs MiMo-V2.6-Flash comparison based on?

57 benchmarks have a result for both models as of October 22, 2026. MiniMax M3's coding index rests on 6 independent benchmarks and MiMo-V2.6-Flash's on 3. 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-m3-vs-xiaomi-mimo-v2-6-flash" title="MiniMax M3 vs MiMo-V2.6-Flash, 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-m3-vs-xiaomi-mimo-v2-6-flash">LLMBenchmark.ai, MiniMax M3 vs MiMo-V2.6-Flash</a></p>