Enter opens the highlighted result. Esc closes.

DeepSeek V3.2 vs Kimi K3

Kimi K3 leads DeepSeek V3.2 on coding, 62.3 to 30.0 on the Vibe Coding Index, and DeepSeek V3.2 costs 17.0x less per output token ($0.88 vs $15.00 per million). Updated October 22, 2026; 58 benchmarks have a result for both.

Replace DeepSeek V3.2 Replace Kimi K3
DeepSeek V3.2DeepSeek
Coding
30.0
Overall
37.9
Output $/M
$0.88
0
Kimi K3Moonshot AI
Coding
62.3
Overall
66.5
Output $/M
$15.00
58
vs boards won of 58 shared

DeepSeek V3.2 or Kimi K3: which to pick

Pick Kimi K3 for coding: it scores 62.3 on the Vibe Coding Index against 30.0 for DeepSeek V3.2.

Pick DeepSeek V3.2 for output tokens 17.0x cheaper ($0.88 vs $15.00 per million).

Model ADeepSeek V3.2DeepSeek30.0/1003 independent benchmarks$0.99 per solved taskModel BKimi K3Moonshot AI62.3/1006 independent benchmarks$0.81 per solved task
Shared results
58
DeepSeek V3.2 only
17
Kimi K3 only
59
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
DeepSeek V3.2 30.0 from 3 benchmarks, Kimi K3 62.3 from 6 benchmarks.
Widest category
Coding, 31.5 points apart on average over 9 shared benchmarks.
Widest single gap
Vibe Code Bench (Vals AI): DeepSeek V3.2 5.1% against Kimi K3 85.0%, 79.9 points apart on a 0 to 100 scale.
Output price
DeepSeek V3.2 $0.88 against Kimi K3 $15.00 per million output tokens, 17.0x apart.
Context window
DeepSeek V3.2 takes 164K 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
CategoryDeepSeek V3.2BarsKimi K3Ties
Coding09
Intelligence02
Agentic work02
Reasoning08
Math02
Knowledge08
Web design07
General020
All shared boards058
CodingLike-for-likeSix of these boards feed the Vibe Coding Index09
Coding benchmarks for DeepSeek V3.2 and Kimi K3
BenchmarkDeepSeek V3.2Kimi K3Leader
SWE-bench Verified70.0%Not measuredOnly DeepSeek V3.2 measured
SWE-bench Multilingual59.0%Not measuredOnly DeepSeek V3.2 measured
LiveBench codingNot measured59.3%Only Kimi K3 measured
LMArena WebDev13621655Kimi K3
AA Coding Index44.276.2Kimi K3
LiveCodeBench (Vals AI)80.7%87.2%Kimi K3
SWE-bench Verified (Vals AI)67.6%93.4%Kimi K3
Terminal-Bench 4 (Vals AI)Not measured17.2%Only Kimi K3 measured
Vibe Code Bench (Vals AI)5.1%85.0%Kimi K3
Code migration (Vals AI)Not measured16.1%Only Kimi K3 measured
ProgramBench (Vals AI)Not measured2.0%Only Kimi K3 measured
IOI (Vals AI)Not measured48.9%Only Kimi K3 measured
Terminal-Bench 2.1 (Vals AI)Not measured80.9%Only Kimi K3 measured
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
CyberBench (Vals AI)Not measured75.2%Only Kimi K3 measured
LiveCodeBench (Artificial Analysis run)86.2%Not measuredOnly DeepSeek V3.2 measured
SciCodeNot measured59.5%Only Kimi K3 measured
Terminal-Bench Hard (Artificial Analysis run)35.6%Not measuredOnly DeepSeek V3.2 measured
Terminal-Bench39.6%Not measuredOnly DeepSeek V3.2 measured
FrontierCodeNot measured44.2%Only Kimi K3 measured
FrontierSWENot measured25.9%Only Kimi K3 measured
WeirdMLNot measured82.6%Only Kimi K3 measured
ALE-BenchNot measured1524.5Only Kimi K3 measured
LMArena Text: coding14531508Kimi K3
LMArena Text: software and IT14491499Kimi K3
LMArena WebDev: React13501670Kimi K3
LMArena WebDev: HTML13711644Kimi K3
LMArena WebDev: from an imageNot measured1579Only Kimi K3 measured
Neither model has a result on the other 10 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index02
Intelligence benchmarks for DeepSeek V3.2 and Kimi K3
BenchmarkDeepSeek V3.2Kimi K3Leader
AA Intelligence Index21.543.6Kimi K3
Epoch Capabilities Index146.1157.9Kimi K3
Agentic workLike-for-likePublic boards, shown as published, kept out of the index02
Agentic work benchmarks for DeepSeek V3.2 and Kimi K3
BenchmarkDeepSeek V3.2Kimi K3Leader
AA Agentic IndexNot measured50.0Only Kimi K3 measured
Design Arena: agents building web appsNot measured1295Only Kimi K3 measured
Design Arena: agents building full-stack appsNot measured1315Only Kimi K3 measured
Design Arena: agents building mobile appsNot measured1269Only Kimi K3 measured
Design Arena: agents building Android appsNot measured1253Only Kimi K3 measured
Design Arena: agents building Godot gamesNot measured1223Only Kimi K3 measured
Design Arena: agents building gamesNot measured1252Only Kimi K3 measured
Design Arena: HTML slidesNot measured1206Only Kimi K3 measured
Design Arena: PowerPoint slidesNot measured1247Only Kimi K3 measured
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 Telecom90.6%Not measuredOnly DeepSeek V3.2 measured
APEX-Agents21.3%47.8%Kimi K3
PostTrainBenchNot measured32.0%Only Kimi K3 measured
Vending-Bench 2$1,034$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 index08
Reasoning benchmarks for DeepSeek V3.2 and Kimi K3
BenchmarkDeepSeek V3.2Kimi K3Leader
GPQA Diamond80.3%92.9%Kimi K3
LiveBench reasoningNot measured90.7%Only Kimi K3 measured
MMMU Pro (Vals AI)Not measured88.2%Only Kimi K3 measured
GPQA Diamond (Artificial Analysis run)84.0%93.5%Kimi K3
Humanity's Last Exam (Artificial Analysis run)24.6%46.9%Kimi K3
GPQA Diamond (Epoch AI run)Not measured93.1%Only Kimi K3 measured
ARC-AGI57.0%94.5%Kimi K3
ARC-AGI-24.0%60.4%Kimi K3
SimpleBenchNot measured60.7%Only Kimi K3 measured
Chess puzzlesNot measured37.0%Only Kimi K3 measured
Mystery game puzzlesNot measured26.0%Only Kimi K3 measured
LMArena Text: hard prompts14341495Kimi K3
LMArena Text: expert14361520Kimi K3
LMArena Text: hard prompts in English14461496Kimi K3
Neither model has a result on the other 8 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index02
Math benchmarks for DeepSeek V3.2 and Kimi K3
BenchmarkDeepSeek V3.2Kimi K3Leader
AIME84.6%Not measuredOnly DeepSeek V3.2 measured
MGSM (Vals AI)86.0%Not measuredOnly DeepSeek V3.2 measured
AA Math Index92.0Not measuredOnly DeepSeek V3.2 measured
AIME 2025 (Artificial Analysis run)92.0%Not measuredOnly DeepSeek V3.2 measured
OTIS Mock AIMENot measured97.2%Only Kimi K3 measured
FrontierMath, tiers 1 to 3Not measured72.2%Only Kimi K3 measured
FrontierMath, tier 4Not measured39.0%Only Kimi K3 measured
ProofBenchNot measured87.0%Only Kimi K3 measured
LMArena Text: math14351494Kimi K3
LMArena Text: mathematical work14401505Kimi K3
Neither model has a result on the other 3 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index08
Knowledge benchmarks for DeepSeek V3.2 and Kimi K3
BenchmarkDeepSeek V3.2Kimi K3Leader
MMLU Pro84.9%88.0%Kimi K3
LegalBench (Vals AI)76.1%86.2%Kimi K3
CaseLaw (Vals AI)55.4%Not measuredOnly DeepSeek V3.2 measured
CorpFin (Vals AI)51.0%71.6%Kimi K3
TaxEval (Vals AI)68.2%75.7%Kimi K3
MortgageTax (Vals AI)Not measured66.3%Only Kimi K3 measured
MedQA (Vals AI)93.9%Not measuredOnly DeepSeek V3.2 measured
MedCode (Vals AI)Not measured49.4%Only Kimi K3 measured
MMLU Pro (Artificial Analysis run)86.2%Not measuredOnly DeepSeek V3.2 measured
SimpleQA VerifiedNot measured50.6%Only Kimi K3 measured
LMArena Text: science14461508Kimi K3
LMArena Text: medicine and healthcare14401489Kimi K3
LMArena Text: legal and government14251503Kimi K3
LMArena Text: business and finance14101470Kimi K3
Neither model has a result on the other 4 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index07
Web design benchmarks for DeepSeek V3.2 and Kimi K3
BenchmarkDeepSeek V3.2Kimi K3Leader
Design Arena: websites11751334Kimi K3
Design Arena: UI components11461341Kimi K3
Design Arena: game dev11311358Kimi K3
Design Arena: data viz11581351Kimi K3
Design Arena: 3D11321387Kimi K3
Design Arena: all code categories11631360Kimi K3
Design Arena: SVG10321302Kimi K3
Design Arena: ASCII art1083Not measuredOnly DeepSeek V3.2 measured
LiveBench designNot measured77.2%Only Kimi K3 measured
GeneralLike-for-likePublic boards, shown as published, kept out of the index020
General benchmarks for DeepSeek V3.2 and Kimi K3
BenchmarkDeepSeek V3.2Kimi 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
IFBench60.7%Not measuredOnly DeepSeek V3.2 measured
Long context reasoning (AA-LCR)73.3%88.7%Kimi K3
DTBench85.6%91.2%Kimi K3
LMCA28.8%52.7%Kimi K3
CL-bench12.4%Not measuredOnly DeepSeek V3.2 measured
Surface Evolver BenchNot measured95.0%Only Kimi K3 measured
Furniture assemblyNot measured34.2%Only Kimi K3 measured
CL-bench Life7.4%Not measuredOnly DeepSeek V3.2 measured
LMArena Text14251476Kimi K3
LMArena Text: instruction following14131485Kimi K3
LMArena Text: creative writing14001457Kimi K3
LMArena Text: English14391481Kimi K3
LMArena Text: non-English14091466Kimi K3
LMArena Text: Chinese14551529Kimi K3
LMArena Text: German14131490Kimi K3
LMArena Text: Japanese13741494Kimi K3
LMArena Text: Korean13701460Kimi K3
LMArena Text: French14291492Kimi K3
LMArena Text: Spanish14241472Kimi K3
LMArena Text: Russian14241485Kimi K3
LMArena Text: Polish14191458Kimi K3
LMArena Text: multi-turn14271489Kimi K3
LMArena Text: longer queries14281494Kimi K3
LMArena Text: writing and language14071471Kimi K3
LMArena Text: entertainment and media13951453Kimi K3
Neither model has a result on the other 15 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for DeepSeek V3.2 and Kimi K3
BenchmarkDeepSeek V3.2Kimi 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

DeepSeek V3.2$0.0007Fits in one request
Kimi K3$0.011Fits in one request

DeepSeek V3.2 costs less

Repository review

50K input + 3K output tokens

DeepSeek V3.2$0.017Fits in one request
Kimi K3$0.195Fits in one request

DeepSeek V3.2 costs less

Agent loop

200K input + 10K output tokens

DeepSeek V3.2$0.067Exceeds the context window
Kimi K3$0.750Fits in one request

DeepSeek V3.2 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 DeepSeek V3.2 and Kimi K3
SpecificationDeepSeek V3.2MoonshotAI Kimi K3
MakerDeepSeekMoonshot AI
WeightsOpen weightsOpen weights
ReleasedDecember 1, 2025July 16, 2026
Context window164K1.05M
Input $/Mtok$0.29$3.00
Output $/Mtok$0.88$15.00
Coding index30.062.3
Independent measurements behind it36
Cost per solved task$0.99$0.81
SourceOpenRouter listingOpenRouter listing

Questions

Is DeepSeek V3.2 better than Kimi K3 for coding?

Pick Kimi K3 for coding: it scores 62.3 on the Vibe Coding Index against 30.0 for DeepSeek V3.2. Pick DeepSeek V3.2 for output tokens 17.0x cheaper ($0.88 vs $15.00 per million).

Which is cheaper, DeepSeek V3.2 or Kimi K3?

DeepSeek V3.2 costs $0.29 per million input tokens and $0.88 per million output tokens; Kimi K3 costs $3.00 and $15.00. Per solved SWE-bench Verified task, DeepSeek V3.2 costs $0.99 and Kimi K3 $0.81.

Which has the bigger context window, DeepSeek V3.2 or Kimi K3?

Kimi K3, with 1.05M tokens against 164K.

How many benchmarks is the DeepSeek V3.2 vs Kimi K3 comparison based on?

58 benchmarks have a result for both models as of October 22, 2026. DeepSeek V3.2's coding index rests on 3 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/deepseek-v3-2-vs-kimi-k3" title="DeepSeek V3.2 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/deepseek-v3-2-vs-kimi-k3">LLMBenchmark.ai, DeepSeek V3.2 vs Kimi K3</a></p>