Enter opens the highlighted result. Esc closes.

Kimi K2.7 Code vs Kimi K3

Kimi K3 leads Kimi K2.7 Code on coding, 62.3 to 53.4 on the Vibe Coding Index, and Kimi K2.7 Code costs 3.8x less per output token ($4.00 vs $15.00 per million). Updated October 22, 2026; 46 benchmarks have a result for both.

Replace Kimi K2.7 Code Replace Kimi K3
Kimi K2.7 CodeMoonshot AI
Coding
53.4
Overall
56.7
Output $/M
$4.00
1
Kimi K3Moonshot AI
Coding
62.3
Overall
66.5
Output $/M
$15.00
45
vs boards won of 46 shared

Kimi K2.7 Code or Kimi K3: which to pick

Pick Kimi K3 for coding: it scores 62.3 on the Vibe Coding Index against 53.4 for Kimi K2.7 Code.

Pick Kimi K2.7 Code for output tokens 3.8x cheaper ($4.00 vs $15.00 per million) and a lower cost per solved task ($0.35 against $0.81).

Model AKimi K2.7 CodeMoonshot AI53.4/1004 independent benchmarks$0.35 per solved taskModel BKimi K3Moonshot AI62.3/1006 independent benchmarks$0.81 per solved task
Shared results
46
Kimi K2.7 Code only
5
Kimi K3 only
71
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 K2.7 Code 53.4 from 4 benchmarks, Kimi K3 62.3 from 6 benchmarks.
Widest category
General, 27.8 points apart on average over 2 shared benchmarks.
Widest single gap
Surface Evolver Bench: Kimi K2.7 Code 48.8% against Kimi K3 95.0%, 46.3 points apart on a 0 to 100 scale.
Output price
Kimi K2.7 Code $4.00 against Kimi K3 $15.00 per million output tokens, 3.8x apart.
Context window
Kimi K2.7 Code takes 262K tokens, Kimi K3 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
CategoryKimi K2.7 CodeBarsKimi K3Ties
Coding114
Intelligence02
Agentic work011
Reasoning05
Math03
Knowledge01
Web design07
General02
All shared boards145
CodingLike-for-likeSix of these boards feed the Vibe Coding Index114
Coding benchmarks for Kimi K2.7 Code and Kimi K3
BenchmarkKimi K2.7 CodeKimi K3Leader
LiveBench codingNot measured59.3%Only Kimi K3 measured
LMArena WebDev14741655Kimi K3
AA Coding Index60.876.2Kimi K3
LiveCodeBench (Vals AI)82.0%87.2%Kimi K3
SWE-bench Verified (Vals AI)78.2%93.4%Kimi K3
Terminal-Bench 4 (Vals AI)Not measured17.2%Only Kimi K3 measured
Vibe Code Bench (Vals AI)47.2%85.0%Kimi K3
Code migration (Vals AI)25.4%16.1%Kimi K2.7 Code
ProgramBench (Vals AI)0.0%2.0%Kimi K3
IOI (Vals AI)Not measured48.9%Only Kimi K3 measured
Terminal-Bench 2.1 (Vals AI)67.0%80.9%Kimi K3
SWE-bench Multimodal (Vals AI)Not measured44.2%Only Kimi K3 measured
Vibe Code Bench 1-100 (Vals AI)Not measured18.2%Only Kimi K3 measured
SkillsBench (Vals AI)50.0%Not measuredOnly Kimi K2.7 Code measured
CyberBench (Vals AI)Not measured75.2%Only Kimi K3 measured
SciCode47.8%59.5%Kimi K3
Terminal-Bench Hard (Artificial Analysis run)44.7%Not measuredOnly Kimi K2.7 Code measured
FrontierCode30.1%44.2%Kimi K3
FrontierSWENot measured25.9%Only Kimi K3 measured
WeirdML54.1%82.6%Kimi K3
ALE-Bench886.21524.5Kimi K3
LMArena Text: codingNot measured1508Only Kimi K3 measured
LMArena Text: software and ITNot measured1499Only Kimi K3 measured
LMArena WebDev: React14751670Kimi K3
LMArena WebDev: HTML14511644Kimi K3
LMArena WebDev: from an image15131579Kimi K3
Neither model has a result on the other 13 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index02
Intelligence benchmarks for Kimi K2.7 Code and Kimi K3
BenchmarkKimi K2.7 CodeKimi K3Leader
AA Intelligence Index25.843.6Kimi K3
Epoch Capabilities Index150.1157.9Kimi K3
Agentic workLike-for-likePublic boards, shown as published, kept out of the index011
Agentic work benchmarks for Kimi K2.7 Code and Kimi K3
BenchmarkKimi K2.7 CodeKimi K3Leader
AA Agentic Index21.050.0Kimi K3
Design Arena: agents building web apps11761295Kimi K3
Design Arena: agents building full-stack apps11751315Kimi K3
Design Arena: agents building mobile apps11431269Kimi K3
Design Arena: agents building Android apps11381253Kimi K3
Design Arena: agents building Godot games11471223Kimi K3
Design Arena: agents building games11301252Kimi K3
Design Arena: HTML slides11511206Kimi K3
Design Arena: PowerPoint slides11291247Kimi K3
Design Arena: spreadsheetsNot measured1070Only Kimi K3 measured
LiveBench researchNot measured79.0%Only Kimi K3 measured
LiveBench browserNot measured16.0%Only Kimi K3 measured
LiveBench long agenticNot measured42.8%Only Kimi K3 measured
Finance Agent (Vals AI)Not measured53.1%Only Kimi K3 measured
Tax Agent Bench (Vals AI)Not measured33.4%Only Kimi K3 measured
Legal Research Bench (Vals AI)Not measured46.1%Only Kimi K3 measured
Harvey's Legal Agent Benchmark (Vals AI)Not measured12.9%Only Kimi K3 measured
Excel Modeling Benchmark (Vals AI)Not measured66.7%Only Kimi K3 measured
BioMysteryBench (Vals AI)Not measured72.6%Only Kimi K3 measured
Terminal-Bench-Science (Vals AI)Not measured1.4%Only Kimi K3 measured
Time Horizon Index (Vals AI)Not measured10.5%Only Kimi K3 measured
τ²-Bench Telecom90.1%Not measuredOnly Kimi K2.7 Code measured
APEX-Agents37.6%47.8%Kimi K3
PostTrainBenchNot measured32.0%Only Kimi K3 measured
Vending-Bench 2$5,083$5,165Kimi K3
Neither model has a result on the other 16 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index05
Reasoning benchmarks for Kimi K2.7 Code and Kimi K3
BenchmarkKimi K2.7 CodeKimi K3Leader
GPQA DiamondNot measured92.9%Only Kimi K3 measured
LiveBench reasoningNot measured90.7%Only Kimi K3 measured
MMMU Pro (Vals AI)Not measured88.2%Only Kimi K3 measured
GPQA Diamond (Artificial Analysis run)89.6%93.5%Kimi K3
Humanity's Last Exam (Artificial Analysis run)35.0%46.9%Kimi K3
GPQA Diamond (Epoch AI run)87.9%93.1%Kimi K3
ARC-AGINot measured94.5%Only Kimi K3 measured
ARC-AGI-2Not measured60.4%Only Kimi K3 measured
SimpleBench57.9%60.7%Kimi K3
Chess puzzles14.0%37.0%Kimi K3
Mystery game puzzlesNot measured26.0%Only Kimi K3 measured
LMArena Text: hard promptsNot measured1495Only Kimi K3 measured
LMArena Text: expertNot measured1520Only Kimi K3 measured
LMArena Text: hard prompts in EnglishNot measured1496Only Kimi K3 measured
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 Kimi K2.7 Code and Kimi K3
BenchmarkKimi K2.7 CodeKimi K3Leader
OTIS Mock AIME95.6%97.2%Kimi K3
FrontierMath, tiers 1 to 354.0%72.2%Kimi K3
FrontierMath, tier 412.2%39.0%Kimi K3
ProofBenchNot measured87.0%Only Kimi K3 measured
LMArena Text: mathNot measured1494Only Kimi K3 measured
LMArena Text: mathematical workNot measured1505Only Kimi K3 measured
Neither model has a result on the other 7 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index01
Knowledge benchmarks for Kimi K2.7 Code and Kimi K3
BenchmarkKimi K2.7 CodeKimi K3Leader
MMLU ProNot measured88.0%Only Kimi K3 measured
LegalBench (Vals AI)Not measured86.2%Only Kimi K3 measured
CorpFin (Vals AI)Not measured71.6%Only Kimi K3 measured
TaxEval (Vals AI)Not measured75.7%Only Kimi K3 measured
MortgageTax (Vals AI)Not measured66.3%Only Kimi K3 measured
MedCode (Vals AI)Not measured49.4%Only Kimi K3 measured
SimpleQA Verified36.5%50.6%Kimi K3
LMArena Text: scienceNot measured1508Only Kimi K3 measured
LMArena Text: medicine and healthcareNot measured1489Only Kimi K3 measured
LMArena Text: legal and governmentNot measured1503Only Kimi K3 measured
LMArena Text: business and financeNot measured1470Only Kimi K3 measured
Neither model has a result on the other 7 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index07
Web design benchmarks for Kimi K2.7 Code and Kimi K3
BenchmarkKimi K2.7 CodeKimi K3Leader
Design Arena: websites12631334Kimi K3
Design Arena: UI components12551341Kimi K3
Design Arena: game dev12201358Kimi K3
Design Arena: data viz12271351Kimi K3
Design Arena: 3D12401387Kimi K3
Design Arena: all code categories12521360Kimi K3
Design Arena: SVG11761302Kimi K3
Design Arena: ASCII art1196Not measuredOnly Kimi K2.7 Code measured
LiveBench designNot measured77.2%Only Kimi K3 measured
GeneralLike-for-likePublic boards, shown as published, kept out of the index02
General benchmarks for Kimi K2.7 Code and Kimi K3
BenchmarkKimi K2.7 CodeKimi K3Leader
Vals IndexNot measured53.0%Only Kimi K3 measured
LiveBench data analysisNot measured78.7%Only Kimi K3 measured
Public Benefits Bench (Vals AI)Not measured68.2%Only Kimi K3 measured
SAGE (Vals AI)Not measured52.8%Only Kimi K3 measured
MedScribe (Vals AI)Not measured88.0%Only Kimi K3 measured
Vals Multimodal IndexNot measured73.4%Only Kimi K3 measured
IFBench63.1%Not measuredOnly Kimi K2.7 Code measured
Long context reasoning (AA-LCR)79.3%88.7%Kimi K3
DTBenchNot measured91.2%Only Kimi K3 measured
LMCANot measured52.7%Only Kimi K3 measured
Surface Evolver Bench48.8%95.0%Kimi K3
Furniture assemblyNot measured34.2%Only Kimi K3 measured
LMArena TextNot measured1476Only Kimi K3 measured
LMArena Text: instruction followingNot measured1485Only Kimi K3 measured
LMArena Text: creative writingNot measured1457Only Kimi K3 measured
LMArena Text: EnglishNot measured1481Only Kimi K3 measured
LMArena Text: non-EnglishNot measured1466Only Kimi K3 measured
LMArena Text: ChineseNot measured1529Only Kimi K3 measured
LMArena Text: GermanNot measured1490Only Kimi K3 measured
LMArena Text: JapaneseNot measured1494Only Kimi K3 measured
LMArena Text: KoreanNot measured1460Only Kimi K3 measured
LMArena Text: FrenchNot measured1492Only Kimi K3 measured
LMArena Text: SpanishNot measured1472Only Kimi K3 measured
LMArena Text: RussianNot measured1485Only Kimi K3 measured
LMArena Text: PolishNot measured1458Only Kimi K3 measured
LMArena Text: multi-turnNot measured1489Only Kimi K3 measured
LMArena Text: longer queriesNot measured1494Only Kimi K3 measured
LMArena Text: writing and languageNot measured1471Only Kimi K3 measured
LMArena Text: entertainment and mediaNot measured1453Only Kimi K3 measured
Neither model has a result on the other 17 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for Kimi K2.7 Code and Kimi K3
BenchmarkKimi K2.7 CodeKimi K3Leader
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 K2.7 Code$0.0029Fits in one request
Kimi K3$0.011Fits in one request

Kimi K2.7 Code costs less

Repository review

50K input + 3K output tokens

Kimi K2.7 Code$0.059Fits in one request
Kimi K3$0.195Fits in one request

Kimi K2.7 Code costs less

Agent loop

200K input + 10K output tokens

Kimi K2.7 Code$0.230Fits in one request
Kimi K3$0.750Fits in one request

Kimi K2.7 Code 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 K2.7 Code and Kimi K3
SpecificationMoonshotAI Kimi K2.7 CodeMoonshotAI Kimi K3
MakerMoonshot AIMoonshot AI
WeightsOpen weightsOpen weights
ReleasedJune 12, 2026July 16, 2026
Context window262K1.05M
Input $/Mtok$0.95$3.00
Output $/Mtok$4.00$15.00
Coding index53.462.3
Independent measurements behind it46
Cost per solved task$0.35$0.81
SourceOpenRouter listingOpenRouter listing

Questions

Is Kimi K2.7 Code better than Kimi K3 for coding?

Pick Kimi K3 for coding: it scores 62.3 on the Vibe Coding Index against 53.4 for Kimi K2.7 Code. Pick Kimi K2.7 Code for output tokens 3.8x cheaper ($4.00 vs $15.00 per million) and a lower cost per solved task ($0.35 against $0.81).

Which is cheaper, Kimi K2.7 Code or Kimi K3?

Kimi K2.7 Code costs $0.95 per million input tokens and $4.00 per million output tokens; Kimi K3 costs $3.00 and $15.00. Per solved SWE-bench Verified task, Kimi K2.7 Code costs $0.35 and Kimi K3 $0.81.

Which has the bigger context window, Kimi K2.7 Code or Kimi K3?

Kimi K3, with 1.05M tokens against 262K.

How many benchmarks is the Kimi K2.7 Code vs Kimi K3 comparison based on?

46 benchmarks have a result for both models as of October 22, 2026. Kimi K2.7 Code's coding index rests on 4 independent benchmarks and Kimi K3'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/kimi-k2-7-code-vs-kimi-k3" title="Kimi K2.7 Code vs Kimi K3, 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-k2-7-code-vs-kimi-k3">LLMBenchmark.ai, Kimi K2.7 Code vs Kimi K3</a></p>