Enter opens the highlighted result. Esc closes.

Kimi K2.6 vs MiniMax M2.7

Kimi K2.6 leads MiniMax M2.7 on coding, 52.1 to 36.2 on the Vibe Coding Index, and MiniMax M2.7 costs 3.3x less per output token ($1.20 vs $4.00 per million). Updated October 22, 2026; 72 benchmarks have a result for both.

Replace Kimi K2.6 Replace MiniMax M2.7
Kimi K2.6Moonshot AI
Coding
52.1
Overall
60.5
Output $/M
$4.00
70
MiniMax M2.7MiniMax
Coding
36.2
Overall
44.5
Output $/M
$1.20
1
vs boards won of 72 shared, 1 tied

Kimi K2.6 or MiniMax M2.7: which to pick

Pick Kimi K2.6 for coding: it scores 52.1 on the Vibe Coding Index against 36.2 for MiniMax M2.7.

Pick MiniMax M2.7 for output tokens 3.3x cheaper ($1.20 vs $4.00 per million) and work measured by MedScribe (Vals AI), where it leads.

Model AKimi K2.6Moonshot AI52.1/1003 independent benchmarks$0.35 per solved taskModel BMiniMax M2.7MiniMax36.2/1003 independent benchmarks$0.64 per solved task
Shared results
72
Kimi K2.6 only
37
MiniMax M2.7 only
2
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
Kimi K2.6 52.1 from 3 benchmarks, MiniMax M2.7 36.2 from 3 benchmarks.
Widest category
Agentic work, 12.3 points apart on average over 6 shared benchmarks.
Widest single gap
LMArena Text: Japanese: Kimi K2.6 1443 against MiniMax M2.7 1260, 30.4 points apart on a 0 to 100 scale.
Output price
Kimi K2.6 $4.00 against MiniMax M2.7 $1.20 per million output tokens, 3.3x apart.
Context window
Kimi K2.6 takes 262K tokens, MiniMax M2.7 205K.

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
CategoryKimi K2.6BarsMiniMax M2.7Ties
Coding1501 tie
Intelligence20
Agentic work60
Reasoning60
Math30
Knowledge100
Web design80
General201
All shared boards7011 tie
CodingLike-for-likeSix of these boards feed the Vibe Coding Index150
Coding benchmarks for Kimi K2.6 and MiniMax M2.7
BenchmarkKimi K2.6MiniMax M2.7Leader
LMArena WebDev15091399Kimi K2.6
AA Coding Index61.852.6Kimi K2.6
LiveCodeBench (Vals AI)86.8%79.9%Kimi K2.6
SWE-bench Verified (Vals AI)76.2%73.8%Kimi K2.6
Vibe Code Bench (Vals AI)37.9%11.9%Kimi K2.6
Code migration (Vals AI)27.8%8.7%Kimi K2.6
ProgramBench (Vals AI)0.0%0.0%Tie
Terminal-Bench 2.1 (Vals AI)53.6%48.7%Kimi K2.6
SciCode51.5%50.1%Kimi K2.6
Terminal-Bench Hard (Artificial Analysis run)43.9%39.4%Kimi K2.6
Terminal-BenchNot measured45.1%Only MiniMax M2.7 measured
WeirdML55.9%37.0%Kimi K2.6
ALE-Bench1092.7599.3Kimi K2.6
LMArena Text: coding14891454Kimi K2.6
LMArena Text: software and IT14841446Kimi K2.6
LMArena WebDev: React15051388Kimi K2.6
LMArena WebDev: HTML14851401Kimi K2.6
LMArena WebDev: from an image1521Not measuredOnly Kimi K2.6 measured
Neither model has a result on the other 21 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
Intelligence benchmarks for Kimi K2.6 and MiniMax M2.7
BenchmarkKimi K2.6MiniMax M2.7Leader
AA Intelligence Index27.022.8Kimi K2.6
Epoch Capabilities Index150.9145.8Kimi K2.6
Agentic workLike-for-likePublic boards, shown as published, kept out of the index60
Agentic work benchmarks for Kimi K2.6 and MiniMax M2.7
BenchmarkKimi K2.6MiniMax M2.7Leader
AA Agentic Index20.515.3Kimi K2.6
Design Arena: agents building web apps1268Not measuredOnly Kimi K2.6 measured
Design Arena: agents building full-stack apps1155Not measuredOnly Kimi K2.6 measured
Design Arena: agents building mobile apps1156Not measuredOnly Kimi K2.6 measured
Design Arena: agents building Android apps1161Not measuredOnly Kimi K2.6 measured
Design Arena: agents building Godot games1120Not measuredOnly Kimi K2.6 measured
Design Arena: agents building games1141Not measuredOnly Kimi K2.6 measured
Design Arena: HTML slides1135Not measuredOnly Kimi K2.6 measured
Design Arena: PowerPoint slides1103Not measuredOnly Kimi K2.6 measured
Design Arena: spreadsheets1276Not measuredOnly Kimi K2.6 measured
Finance Agent (Vals AI)44.9%27.9%Kimi K2.6
Tax Agent Bench (Vals AI)12.4%6.9%Kimi K2.6
Legal Research Bench (Vals AI)15.9%10.6%Kimi K2.6
Excel Modeling Benchmark (Vals AI)57.9%28.4%Kimi K2.6
τ²-Bench Telecom95.9%84.8%Kimi K2.6
OSWorld 2.04.6%Not measuredOnly Kimi K2.6 measured
Vending-Bench 2$6,205Not measuredOnly Kimi K2.6 measured
Neither model has a result on the other 24 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index60
Reasoning benchmarks for Kimi K2.6 and MiniMax M2.7
BenchmarkKimi K2.6MiniMax M2.7Leader
GPQA Diamond89.1%86.6%Kimi K2.6
MMMU Pro (Vals AI)86.3%Not measuredOnly Kimi K2.6 measured
GPQA Diamond (Artificial Analysis run)91.1%87.4%Kimi K2.6
Humanity's Last Exam (Artificial Analysis run)37.5%29.6%Kimi K2.6
GPQA Diamond (Epoch AI run)90.8%Not measuredOnly Kimi K2.6 measured
Chess puzzles20.0%Not measuredOnly Kimi K2.6 measured
Mystery game puzzles18.0%Not measuredOnly Kimi K2.6 measured
EBR-bench2.4%Not measuredOnly Kimi K2.6 measured
LMArena Text: hard prompts14701422Kimi K2.6
LMArena Text: expert14911443Kimi K2.6
LMArena Text: hard prompts in English14711441Kimi K2.6
LMArena Vision: diagrams1298Not measuredOnly Kimi K2.6 measured
LMArena Vision: homework1310Not measuredOnly Kimi K2.6 measured
Neither model has a result on the other 9 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index30
Math benchmarks for Kimi K2.6 and MiniMax M2.7
BenchmarkKimi K2.6MiniMax M2.7Leader
AIMENot measured91.0%Only MiniMax M2.7 measured
OTIS Mock AIME96.1%Not measuredOnly Kimi K2.6 measured
FrontierMath, tiers 1 to 357.2%Not measuredOnly Kimi K2.6 measured
FrontierMath, tier 425.6%Not measuredOnly Kimi K2.6 measured
ProofBench16.0%3.0%Kimi K2.6
LMArena Text: math14741421Kimi K2.6
LMArena Text: mathematical work14801437Kimi K2.6
Neither model has a result on the other 6 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index100
Knowledge benchmarks for Kimi K2.6 and MiniMax M2.7
BenchmarkKimi K2.6MiniMax M2.7Leader
MMLU Pro87.6%80.4%Kimi K2.6
LegalBench (Vals AI)84.7%84.0%Kimi K2.6
CaseLaw (Vals AI)61.2%60.9%Kimi K2.6
CorpFin (Vals AI)66.7%61.2%Kimi K2.6
TaxEval (Vals AI)74.7%66.6%Kimi K2.6
MortgageTax (Vals AI)65.8%Not measuredOnly Kimi K2.6 measured
MedCode (Vals AI)40.1%34.4%Kimi K2.6
SimpleQA Verified34.9%Not measuredOnly Kimi K2.6 measured
LMArena Text: science14681416Kimi K2.6
LMArena Text: medicine and healthcare14571409Kimi K2.6
LMArena Text: legal and government14621403Kimi K2.6
LMArena Text: business and finance14451407Kimi K2.6
Neither model has a result on the other 6 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index80
Web design benchmarks for Kimi K2.6 and MiniMax M2.7
BenchmarkKimi K2.6MiniMax M2.7Leader
Design Arena: websites12681243Kimi K2.6
Design Arena: UI components12631210Kimi K2.6
Design Arena: game dev12501209Kimi K2.6
Design Arena: data viz12491233Kimi K2.6
Design Arena: 3D12671195Kimi K2.6
Design Arena: all code categories12711233Kimi K2.6
Design Arena: SVG11811137Kimi K2.6
Design Arena: ASCII art11651136Kimi K2.6
Neither model has a result on the other 1 board here
GeneralLike-for-likePublic boards, shown as published, kept out of the index201
General benchmarks for Kimi K2.6 and MiniMax M2.7
BenchmarkKimi K2.6MiniMax M2.7Leader
Public Benefits Bench (Vals AI)56.6%Not measuredOnly Kimi K2.6 measured
SAGE (Vals AI)50.2%Not measuredOnly Kimi K2.6 measured
MedScribe (Vals AI)78.2%79.9%MiniMax M2.7
Vals Multimodal Index56.4%Not measuredOnly Kimi K2.6 measured
IFBench76.0%75.7%Kimi K2.6
Long context reasoning (AA-LCR)81.0%78.3%Kimi K2.6
DTBench90.9%Not measuredOnly Kimi K2.6 measured
LMCA37.3%Not measuredOnly Kimi K2.6 measured
Furniture assembly21.7%Not measuredOnly Kimi K2.6 measured
ExploitBench18.4%13.3%Kimi K2.6
LMArena Text14551405Kimi K2.6
LMArena Text: instruction following14511405Kimi K2.6
LMArena Text: creative writing14341354Kimi K2.6
LMArena Vision1282Not measuredOnly Kimi K2.6 measured
LMArena Text: English14601426Kimi K2.6
LMArena Text: non-English14461382Kimi K2.6
LMArena Text: Chinese15201442Kimi K2.6
LMArena Text: German14511398Kimi K2.6
LMArena Text: Japanese14431260Kimi K2.6
LMArena Text: Korean14271314Kimi K2.6
LMArena Text: French14711424Kimi K2.6
LMArena Text: Spanish14641402Kimi K2.6
LMArena Text: Russian14461383Kimi K2.6
LMArena Text: Polish14381387Kimi K2.6
LMArena Text: multi-turn14531412Kimi K2.6
LMArena Text: longer queries14681418Kimi K2.6
LMArena Text: writing and language14391376Kimi K2.6
LMArena Text: entertainment and media14281360Kimi K2.6
LMArena Vision: English1287Not measuredOnly Kimi K2.6 measured
LMArena Vision: Chinese1346Not measuredOnly Kimi K2.6 measured
LMArena Vision: reading text1291Not measuredOnly Kimi K2.6 measured
LMArena Vision: humor1280Not measuredOnly Kimi K2.6 measured
LMArena Vision: creative writing1273Not measuredOnly Kimi K2.6 measured
LMArena Document1451Not measuredOnly Kimi K2.6 measured
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 Kimi K2.6 and MiniMax M2.7
BenchmarkKimi K2.6MiniMax M2.7Leader
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

Kimi K2.6$0.0029Fits in one request
MiniMax M2.7$0.0009Fits in one request

MiniMax M2.7 costs less

Repository review

50K input + 3K output tokens

Kimi K2.6$0.059Fits in one request
MiniMax M2.7$0.019Fits in one request

MiniMax M2.7 costs less

Agent loop

200K input + 10K output tokens

Kimi K2.6$0.230Fits in one request
MiniMax M2.7$0.072Exceeds the context window

MiniMax M2.7 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 Kimi K2.6 and MiniMax M2.7
SpecificationMoonshotAI Kimi K2.6MiniMax M2.7
MakerMoonshot AIMiniMax
WeightsOpen weightsOpen weights
ReleasedApril 20, 2026March 18, 2026
Context window262K205K
Input $/Mtok$0.95$0.30
Output $/Mtok$4.00$1.20
Coding index52.136.2
Independent measurements behind it33
Cost per solved task$0.35$0.64
SourceOpenRouter listingOpenRouter listing

Questions

Is Kimi K2.6 better than MiniMax M2.7 for coding?

Pick Kimi K2.6 for coding: it scores 52.1 on the Vibe Coding Index against 36.2 for MiniMax M2.7. Pick MiniMax M2.7 for output tokens 3.3x cheaper ($1.20 vs $4.00 per million) and work measured by MedScribe (Vals AI), where it leads.

Which is cheaper, Kimi K2.6 or MiniMax M2.7?

Kimi K2.6 costs $0.95 per million input tokens and $4.00 per million output tokens; MiniMax M2.7 costs $0.30 and $1.20. Per solved SWE-bench Verified task, Kimi K2.6 costs $0.35 and MiniMax M2.7 $0.64.

Which has the bigger context window, Kimi K2.6 or MiniMax M2.7?

Kimi K2.6, with 262K tokens against 205K.

How many benchmarks is the Kimi K2.6 vs MiniMax M2.7 comparison based on?

72 benchmarks have a result for both models as of October 22, 2026. Kimi K2.6's coding index rests on 3 independent benchmarks and MiniMax M2.7'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/kimi-k2-6-vs-minimax-minimax-m2-7" title="Kimi K2.6 vs MiniMax M2.7, 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/kimi-k2-6-vs-minimax-minimax-m2-7">LLMBenchmark.ai, Kimi K2.6 vs MiniMax M2.7</a></p>