Enter opens the highlighted result. Esc closes.

Kimi K2.5 vs MiniMax M2.5

Kimi K2.5 leads MiniMax M2.5 on coding, 38.6 to 37.2 on the Vibe Coding Index, and MiniMax M2.5 costs 2.4x less per output token ($1.20 vs $2.85 per million). Updated October 22, 2026; 66 benchmarks have a result for both.

Replace Kimi K2.5 Replace MiniMax M2.5
Kimi K2.5Moonshot AI
Coding
38.6
Overall
44.8
Output $/M
$2.85
60
MiniMax M2.5MiniMax
Coding
37.2
Overall
37.3
Output $/M
$1.20
5
vs boards won of 66 shared, 1 tied

Kimi K2.5 or MiniMax M2.5: which to pick

Kimi K2.5 and MiniMax M2.5 are level for coding, 38.6 against 37.2 on the Vibe Coding Index, so price and context decide.

Pick MiniMax M2.5 for output tokens 2.4x cheaper ($1.20 vs $2.85 per million) and work measured by SWE-bench Verified or SWE-bench Multilingual, where it leads. Pick Kimi K2.5 for a lower cost per solved task ($0.24 against $0.62) and a larger context window (262K against 205K tokens).

Model AKimi K2.5Moonshot AI38.6/1003 independent benchmarks$0.24 per solved taskModel BMiniMax M2.5MiniMax37.2/1003 independent benchmarks$0.62 per solved task
Shared results
66
Kimi K2.5 only
33
MiniMax M2.5 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 K2.5 38.6 from 3 benchmarks, MiniMax M2.5 37.2 from 3 benchmarks.
Widest category
General, 14.8 points apart on average over 21 shared benchmarks.
Widest single gap
LMArena Text: Japanese: Kimi K2.5 1423 against MiniMax M2.5 1171, 41.9 points apart on a 0 to 100 scale.
Output price
Kimi K2.5 $2.85 against MiniMax M2.5 $1.20 per million output tokens, 2.4x apart.
Context window
Kimi K2.5 takes 262K tokens, MiniMax M2.5 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 K2.5BarsMiniMax M2.5Ties
Coding931 tie
Intelligence20
Agentic work20
Reasoning90
Math30
Knowledge90
Web design61
General201
All shared boards6051 tie
CodingLike-for-likeSix of these boards feed the Vibe Coding Index93
Coding benchmarks for Kimi K2.5 and MiniMax M2.5
BenchmarkKimi K2.5MiniMax M2.5Leader
SWE-bench Verified70.8%75.8%MiniMax M2.5
SWE-bench Multilingual67.3%68.3%MiniMax M2.5
LMArena WebDev14371386Kimi K2.5
AA Coding Index46.8Not measuredOnly Kimi K2.5 measured
LiveCodeBench (Vals AI)83.9%79.2%Kimi K2.5
SWE-bench Verified (Vals AI)70.0%74.2%MiniMax M2.5
Vibe Code Bench (Vals AI)17.5%14.8%Kimi K2.5
Code migration (Vals AI)7.0%Not measuredOnly Kimi K2.5 measured
Terminal-Bench 2.1 (Vals AI)42.0%Not measuredOnly Kimi K2.5 measured
Terminal-Bench Hard (Artificial Analysis run)34.8%34.8%Tie
Terminal-Bench43.2%42.7%Kimi K2.5
WeirdML45.6%Not measuredOnly Kimi K2.5 measured
ALE-Bench821.6618.2Kimi K2.5
LMArena Text: coding14831380Kimi K2.5
LMArena Text: software and IT14711383Kimi K2.5
LMArena WebDev: React14291374Kimi K2.5
LMArena WebDev: HTML14261414Kimi K2.5
LMArena WebDev: from an image1439Not measuredOnly Kimi K2.5 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 K2.5 and MiniMax M2.5
BenchmarkKimi K2.5MiniMax M2.5Leader
AA Intelligence Index23.522.8Kimi K2.5
Epoch Capabilities Index148.1146.6Kimi K2.5
Agentic workLike-for-likePublic boards, shown as published, kept out of the index20
Agentic work benchmarks for Kimi K2.5 and MiniMax M2.5
BenchmarkKimi K2.5MiniMax M2.5Leader
Design Arena: agents building web apps1136Not measuredOnly Kimi K2.5 measured
Design Arena: agents building full-stack apps1114Not measuredOnly Kimi K2.5 measured
Design Arena: agents building mobile apps1147Not measuredOnly Kimi K2.5 measured
Design Arena: agents building Android apps1118Not measuredOnly Kimi K2.5 measured
Design Arena: agents building Godot games1219Not measuredOnly Kimi K2.5 measured
Finance Agent (Vals AI)35.8%Not measuredOnly Kimi K2.5 measured
Legal Research Bench (Vals AI)15.9%Not measuredOnly Kimi K2.5 measured
Excel Modeling Benchmark (Vals AI)28.5%Not measuredOnly Kimi K2.5 measured
τ²-Bench Telecom95.9%95.3%Kimi K2.5
OSWorld63.3%Not measuredOnly Kimi K2.5 measured
Vending-Bench 2$1,198-$23Kimi K2.5
Neither model has a result on the other 30 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index90
Reasoning benchmarks for Kimi K2.5 and MiniMax M2.5
BenchmarkKimi K2.5MiniMax M2.5Leader
GPQA Diamond84.1%82.1%Kimi K2.5
MMMU Pro (Vals AI)84.3%Not measuredOnly Kimi K2.5 measured
GPQA Diamond (Artificial Analysis run)87.9%84.8%Kimi K2.5
Humanity's Last Exam (Artificial Analysis run)30.7%20.5%Kimi K2.5
ARC-AGI65.3%63.7%Kimi K2.5
ARC-AGI-211.8%4.9%Kimi K2.5
SimpleBench46.8%Not measuredOnly Kimi K2.5 measured
LMArena Text: hard prompts14531372Kimi K2.5
LMArena Text: expert14661378Kimi K2.5
LMArena Text: hard prompts in English14601384Kimi K2.5
LMArena Vision: diagrams1282Not measuredOnly Kimi K2.5 measured
LMArena Vision: homework1297Not measuredOnly Kimi K2.5 measured
Kagi LLM Benchmark78.5%55.2%Kimi K2.5
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 K2.5 and MiniMax M2.5
BenchmarkKimi K2.5MiniMax M2.5Leader
AIME95.6%88.8%Kimi K2.5
ProofBenchNot measured4.0%Only MiniMax M2.5 measured
LMArena Text: math14701378Kimi K2.5
LMArena Text: mathematical work14731378Kimi K2.5
Neither model has a result on the other 9 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index90
Knowledge benchmarks for Kimi K2.5 and MiniMax M2.5
BenchmarkKimi K2.5MiniMax M2.5Leader
MMLU Pro85.9%80.1%Kimi K2.5
LegalBench (Vals AI)Not measured80.0%Only MiniMax M2.5 measured
CaseLaw (Vals AI)58.7%53.5%Kimi K2.5
CorpFin (Vals AI)68.3%59.6%Kimi K2.5
TaxEval (Vals AI)74.2%68.2%Kimi K2.5
MortgageTax (Vals AI)66.5%Not measuredOnly Kimi K2.5 measured
MedQA (Vals AI)94.4%92.5%Kimi K2.5
MedCode (Vals AI)39.3%Not measuredOnly Kimi K2.5 measured
SimpleQA Verified34.3%Not measuredOnly Kimi K2.5 measured
LMArena Text: science14591369Kimi K2.5
LMArena Text: medicine and healthcare14481357Kimi K2.5
LMArena Text: legal and government14411366Kimi K2.5
LMArena Text: business and finance14271356Kimi K2.5
Neither model has a result on the other 5 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index61
Web design benchmarks for Kimi K2.5 and MiniMax M2.5
BenchmarkKimi K2.5MiniMax M2.5Leader
Design Arena: websites12481222Kimi K2.5
Design Arena: UI components12341173Kimi K2.5
Design Arena: game dev12061176Kimi K2.5
Design Arena: data viz12191172Kimi K2.5
Design Arena: 3D12041170Kimi K2.5
Design Arena: all code categories12361207Kimi K2.5
Design Arena: SVG11491150MiniMax M2.5
Design Arena: ASCII art1166Not measuredOnly Kimi K2.5 measured
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 K2.5 and MiniMax M2.5
BenchmarkKimi K2.5MiniMax M2.5Leader
SAGE (Vals AI)49.9%Not measuredOnly Kimi K2.5 measured
MedScribe (Vals AI)76.4%Not measuredOnly Kimi K2.5 measured
IFBench70.2%71.6%MiniMax M2.5
Long context reasoning (AA-LCR)78.0%73.3%Kimi K2.5
Fiction.LiveBench86.1%Not measuredOnly Kimi K2.5 measured
CL-bench19.3%11.4%Kimi K2.5
CL-bench Life13.2%6.3%Kimi K2.5
LMArena Text14451359Kimi K2.5
LMArena Text: instruction following14311353Kimi K2.5
LMArena Text: creative writing14221331Kimi K2.5
LMArena Vision1269Not measuredOnly Kimi K2.5 measured
LMArena Text: English14531380Kimi K2.5
LMArena Text: non-English14331338Kimi K2.5
LMArena Text: Chinese14941393Kimi K2.5
LMArena Text: German14411361Kimi K2.5
LMArena Text: Japanese14231171Kimi K2.5
LMArena Text: Korean14121233Kimi K2.5
LMArena Text: French14541363Kimi K2.5
LMArena Text: Spanish14501353Kimi K2.5
LMArena Text: Russian14351359Kimi K2.5
LMArena Text: Polish14451334Kimi K2.5
LMArena Text: multi-turn14441364Kimi K2.5
LMArena Text: longer queries14451366Kimi K2.5
LMArena Text: writing and language14251345Kimi K2.5
LMArena Text: entertainment and media14171329Kimi K2.5
LMArena Vision: English1274Not measuredOnly Kimi K2.5 measured
LMArena Vision: Chinese1328Not measuredOnly Kimi K2.5 measured
LMArena Vision: reading text1276Not measuredOnly Kimi K2.5 measured
LMArena Vision: humor1284Not measuredOnly Kimi K2.5 measured
LMArena Vision: captioning1257Not measuredOnly Kimi K2.5 measured
LMArena Vision: recognizing things1285Not measuredOnly Kimi K2.5 measured
LMArena Vision: creative writing1269Not measuredOnly Kimi K2.5 measured
Neither model has a result on the other 14 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for Kimi K2.5 and MiniMax M2.5
BenchmarkKimi K2.5MiniMax M2.5Leader
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 K2.5$0.0020Fits in one request
MiniMax M2.5$0.0009Fits in one request

MiniMax M2.5 costs less

Repository review

50K input + 3K output tokens

Kimi K2.5$0.035Fits in one request
MiniMax M2.5$0.019Fits in one request

MiniMax M2.5 costs less

Agent loop

200K input + 10K output tokens

Kimi K2.5$0.135Fits in one request
MiniMax M2.5$0.072Exceeds the context window

MiniMax M2.5 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 K2.5 and MiniMax M2.5
SpecificationMoonshotAI Kimi K2.5MiniMax M2.5
MakerMoonshot AIMiniMax
WeightsOpen weightsOpen weights
ReleasedJanuary 27, 2026February 12, 2026
Context window262K205K
Input $/Mtok$0.532$0.30
Output $/Mtok$2.85$1.20
Coding index38.637.2
Independent measurements behind it33
Cost per solved task$0.24$0.62
SourceOpenRouter listingOpenRouter listing

Questions

Is Kimi K2.5 better than MiniMax M2.5 for coding?

Kimi K2.5 and MiniMax M2.5 are level for coding, 38.6 against 37.2 on the Vibe Coding Index, so price and context decide. Pick MiniMax M2.5 for output tokens 2.4x cheaper ($1.20 vs $2.85 per million) and work measured by SWE-bench Verified or SWE-bench Multilingual, where it leads. Pick Kimi K2.5 for a lower cost per solved task ($0.24 against $0.62) and a larger context window (262K against 205K tokens).

Which is cheaper, Kimi K2.5 or MiniMax M2.5?

Kimi K2.5 costs $0.532 per million input tokens and $2.85 per million output tokens; MiniMax M2.5 costs $0.30 and $1.20. Per solved SWE-bench Verified task, Kimi K2.5 costs $0.24 and MiniMax M2.5 $0.62.

Which has the bigger context window, Kimi K2.5 or MiniMax M2.5?

Kimi K2.5, with 262K tokens against 205K.

How many benchmarks is the Kimi K2.5 vs MiniMax M2.5 comparison based on?

66 benchmarks have a result for both models as of October 22, 2026. Kimi K2.5's coding index rests on 3 independent benchmarks and MiniMax M2.5'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-k2-5-vs-minimax-minimax-m2-5" title="Kimi K2.5 vs MiniMax M2.5, 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-k2-5-vs-minimax-minimax-m2-5">LLMBenchmark.ai, Kimi K2.5 vs MiniMax M2.5</a></p>