Enter opens the highlighted result. Esc closes.

DeepSeek V3.2 vs Kimi K2.5

Kimi K2.5 leads DeepSeek V3.2 on coding, 38.6 to 30.0 on the Vibe Coding Index, and DeepSeek V3.2 costs 3.2x less per output token ($0.88 vs $2.85 per million). Updated October 22, 2026; 66 benchmarks have a result for both.

Replace DeepSeek V3.2 Replace Kimi K2.5
DeepSeek V3.2DeepSeek
Coding
30.0
Overall
37.9
Output $/M
$0.88
1
Kimi K2.5Moonshot AI
Coding
38.6
Overall
44.8
Output $/M
$2.85
65
vs boards won of 66 shared

DeepSeek V3.2 or Kimi K2.5: which to pick

Pick Kimi K2.5 for coding: it scores 38.6 on the Vibe Coding Index against 30.0 for DeepSeek V3.2.

Pick DeepSeek V3.2 for output tokens 3.2x cheaper ($0.88 vs $2.85 per million) and work measured by Terminal-Bench Hard (Artificial Analysis run), where it leads.

Model ADeepSeek V3.2DeepSeek30.0/1003 independent benchmarks$0.99 per solved taskModel BKimi K2.5Moonshot AI38.6/1003 independent benchmarks$0.24 per solved task
Shared results
66
DeepSeek V3.2 only
9
Kimi K2.5 only
33
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 K2.5 38.6 from 3 benchmarks.
Widest category
Web design, 10.0 points apart on average over 8 shared benchmarks.
Widest single gap
CorpFin (Vals AI): DeepSeek V3.2 51.0% against Kimi K2.5 68.3%, 17.3 points apart on a 0 to 100 scale.
Output price
DeepSeek V3.2 $0.88 against Kimi K2.5 $2.85 per million output tokens, 3.2x apart.
Context window
DeepSeek V3.2 takes 164K tokens, Kimi K2.5 262K.

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 K2.5Ties
Coding112
Intelligence02
Agentic work02
Reasoning08
Math03
Knowledge09
Web design08
General021
All shared boards165
CodingLike-for-likeSix of these boards feed the Vibe Coding Index112
Coding benchmarks for DeepSeek V3.2 and Kimi K2.5
BenchmarkDeepSeek V3.2Kimi K2.5Leader
SWE-bench Verified70.0%70.8%Kimi K2.5
SWE-bench Multilingual59.0%67.3%Kimi K2.5
LMArena WebDev13621437Kimi K2.5
AA Coding Index44.246.8Kimi K2.5
LiveCodeBench (Vals AI)80.7%83.9%Kimi K2.5
SWE-bench Verified (Vals AI)67.6%70.0%Kimi K2.5
Vibe Code Bench (Vals AI)5.1%17.5%Kimi K2.5
Code migration (Vals AI)Not measured7.0%Only Kimi K2.5 measured
Terminal-Bench 2.1 (Vals AI)Not measured42.0%Only Kimi K2.5 measured
LiveCodeBench (Artificial Analysis run)86.2%Not measuredOnly DeepSeek V3.2 measured
Terminal-Bench Hard (Artificial Analysis run)35.6%34.8%DeepSeek V3.2
Terminal-Bench39.6%43.2%Kimi K2.5
WeirdMLNot measured45.6%Only Kimi K2.5 measured
ALE-BenchNot measured821.6Only Kimi K2.5 measured
LMArena Text: coding14531483Kimi K2.5
LMArena Text: software and IT14491471Kimi K2.5
LMArena WebDev: React13501429Kimi K2.5
LMArena WebDev: HTML13711426Kimi K2.5
LMArena WebDev: from an imageNot measured1439Only Kimi K2.5 measured
Neither model has a result on the other 20 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index02
Intelligence benchmarks for DeepSeek V3.2 and Kimi K2.5
BenchmarkDeepSeek V3.2Kimi K2.5Leader
AA Intelligence Index21.523.5Kimi K2.5
Epoch Capabilities Index146.1148.1Kimi K2.5
Agentic workLike-for-likePublic boards, shown as published, kept out of the index02
Agentic work benchmarks for DeepSeek V3.2 and Kimi K2.5
BenchmarkDeepSeek V3.2Kimi K2.5Leader
Design Arena: agents building web appsNot measured1136Only Kimi K2.5 measured
Design Arena: agents building full-stack appsNot measured1114Only Kimi K2.5 measured
Design Arena: agents building mobile appsNot measured1147Only Kimi K2.5 measured
Design Arena: agents building Android appsNot measured1118Only Kimi K2.5 measured
Design Arena: agents building Godot gamesNot measured1219Only Kimi K2.5 measured
Finance Agent (Vals AI)Not measured35.8%Only Kimi K2.5 measured
Legal Research Bench (Vals AI)Not measured15.9%Only Kimi K2.5 measured
Excel Modeling Benchmark (Vals AI)Not measured28.5%Only Kimi K2.5 measured
τ²-Bench Telecom90.6%95.9%Kimi K2.5
APEX-Agents21.3%Not measuredOnly DeepSeek V3.2 measured
OSWorldNot measured63.3%Only Kimi K2.5 measured
Vending-Bench 2$1,034$1,198Kimi K2.5
Neither model has a result on the other 29 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index08
Reasoning benchmarks for DeepSeek V3.2 and Kimi K2.5
BenchmarkDeepSeek V3.2Kimi K2.5Leader
GPQA Diamond80.3%84.1%Kimi K2.5
MMMU Pro (Vals AI)Not measured84.3%Only Kimi K2.5 measured
GPQA Diamond (Artificial Analysis run)84.0%87.9%Kimi K2.5
Humanity's Last Exam (Artificial Analysis run)24.6%30.7%Kimi K2.5
ARC-AGI57.0%65.3%Kimi K2.5
ARC-AGI-24.0%11.8%Kimi K2.5
SimpleBenchNot measured46.8%Only Kimi K2.5 measured
LMArena Text: hard prompts14341453Kimi K2.5
LMArena Text: expert14361466Kimi K2.5
LMArena Text: hard prompts in English14461460Kimi K2.5
LMArena Vision: diagramsNot measured1282Only Kimi K2.5 measured
LMArena Vision: homeworkNot measured1297Only Kimi K2.5 measured
Kagi LLM BenchmarkNot measured78.5%Only Kimi K2.5 measured
Neither model has a result on the other 9 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index03
Math benchmarks for DeepSeek V3.2 and Kimi K2.5
BenchmarkDeepSeek V3.2Kimi K2.5Leader
AIME84.6%95.6%Kimi K2.5
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
LMArena Text: math14351470Kimi K2.5
LMArena Text: mathematical work14401473Kimi K2.5
Neither model has a result on the other 7 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index09
Knowledge benchmarks for DeepSeek V3.2 and Kimi K2.5
BenchmarkDeepSeek V3.2Kimi K2.5Leader
MMLU Pro84.9%85.9%Kimi K2.5
LegalBench (Vals AI)76.1%Not measuredOnly DeepSeek V3.2 measured
CaseLaw (Vals AI)55.4%58.7%Kimi K2.5
CorpFin (Vals AI)51.0%68.3%Kimi K2.5
TaxEval (Vals AI)68.2%74.2%Kimi K2.5
MortgageTax (Vals AI)Not measured66.5%Only Kimi K2.5 measured
MedQA (Vals AI)93.9%94.4%Kimi K2.5
MedCode (Vals AI)Not measured39.3%Only Kimi K2.5 measured
MMLU Pro (Artificial Analysis run)86.2%Not measuredOnly DeepSeek V3.2 measured
SimpleQA VerifiedNot measured34.3%Only Kimi K2.5 measured
LMArena Text: science14461459Kimi K2.5
LMArena Text: medicine and healthcare14401448Kimi K2.5
LMArena Text: legal and government14251441Kimi K2.5
LMArena Text: business and finance14101427Kimi K2.5
Neither model has a result on the other 4 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index08
Web design benchmarks for DeepSeek V3.2 and Kimi K2.5
BenchmarkDeepSeek V3.2Kimi K2.5Leader
Design Arena: websites11751248Kimi K2.5
Design Arena: UI components11461234Kimi K2.5
Design Arena: game dev11311206Kimi K2.5
Design Arena: data viz11581219Kimi K2.5
Design Arena: 3D11321204Kimi K2.5
Design Arena: all code categories11631236Kimi K2.5
Design Arena: SVG10321149Kimi K2.5
Design Arena: ASCII art10831166Kimi K2.5
Neither model has a result on the other 1 board here
GeneralLike-for-likePublic boards, shown as published, kept out of the index021
General benchmarks for DeepSeek V3.2 and Kimi K2.5
BenchmarkDeepSeek V3.2Kimi K2.5Leader
SAGE (Vals AI)Not measured49.9%Only Kimi K2.5 measured
MedScribe (Vals AI)Not measured76.4%Only Kimi K2.5 measured
IFBench60.7%70.2%Kimi K2.5
Long context reasoning (AA-LCR)73.3%78.0%Kimi K2.5
DTBench85.6%Not measuredOnly DeepSeek V3.2 measured
LMCA28.8%Not measuredOnly DeepSeek V3.2 measured
Fiction.LiveBenchNot measured86.1%Only Kimi K2.5 measured
CL-bench12.4%19.3%Kimi K2.5
CL-bench Life7.4%13.2%Kimi K2.5
LMArena Text14251445Kimi K2.5
LMArena Text: instruction following14131431Kimi K2.5
LMArena Text: creative writing14001422Kimi K2.5
LMArena VisionNot measured1269Only Kimi K2.5 measured
LMArena Text: English14391453Kimi K2.5
LMArena Text: non-English14091433Kimi K2.5
LMArena Text: Chinese14551494Kimi K2.5
LMArena Text: German14131441Kimi K2.5
LMArena Text: Japanese13741423Kimi K2.5
LMArena Text: Korean13701412Kimi K2.5
LMArena Text: French14291454Kimi K2.5
LMArena Text: Spanish14241450Kimi K2.5
LMArena Text: Russian14241435Kimi K2.5
LMArena Text: Polish14191445Kimi K2.5
LMArena Text: multi-turn14271444Kimi K2.5
LMArena Text: longer queries14281445Kimi K2.5
LMArena Text: writing and language14071425Kimi K2.5
LMArena Text: entertainment and media13951417Kimi K2.5
LMArena Vision: EnglishNot measured1274Only Kimi K2.5 measured
LMArena Vision: ChineseNot measured1328Only Kimi K2.5 measured
LMArena Vision: reading textNot measured1276Only Kimi K2.5 measured
LMArena Vision: humorNot measured1284Only Kimi K2.5 measured
LMArena Vision: captioningNot measured1257Only Kimi K2.5 measured
LMArena Vision: recognizing thingsNot measured1285Only Kimi K2.5 measured
LMArena Vision: creative writingNot measured1269Only Kimi K2.5 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 DeepSeek V3.2 and Kimi K2.5
BenchmarkDeepSeek V3.2Kimi K2.5Leader
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

DeepSeek V3.2$0.0007Fits in one request
Kimi K2.5$0.0020Fits in one request

DeepSeek V3.2 costs less

Repository review

50K input + 3K output tokens

DeepSeek V3.2$0.017Fits in one request
Kimi K2.5$0.035Fits in one request

DeepSeek V3.2 costs less

Agent loop

200K input + 10K output tokens

DeepSeek V3.2$0.067Exceeds the context window
Kimi K2.5$0.135Fits 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 K2.5
SpecificationDeepSeek V3.2MoonshotAI Kimi K2.5
MakerDeepSeekMoonshot AI
WeightsOpen weightsOpen weights
ReleasedDecember 1, 2025January 27, 2026
Context window164K262K
Input $/Mtok$0.29$0.532
Output $/Mtok$0.88$2.85
Coding index30.038.6
Independent measurements behind it33
Cost per solved task$0.99$0.24
SourceOpenRouter listingOpenRouter listing

Questions

Is DeepSeek V3.2 better than Kimi K2.5 for coding?

Pick Kimi K2.5 for coding: it scores 38.6 on the Vibe Coding Index against 30.0 for DeepSeek V3.2. Pick DeepSeek V3.2 for output tokens 3.2x cheaper ($0.88 vs $2.85 per million) and work measured by Terminal-Bench Hard (Artificial Analysis run), where it leads.

Which is cheaper, DeepSeek V3.2 or Kimi K2.5?

DeepSeek V3.2 costs $0.29 per million input tokens and $0.88 per million output tokens; Kimi K2.5 costs $0.532 and $2.85. Per solved SWE-bench Verified task, DeepSeek V3.2 costs $0.99 and Kimi K2.5 $0.24.

Which has the bigger context window, DeepSeek V3.2 or Kimi K2.5?

Kimi K2.5, with 262K tokens against 164K.

How many benchmarks is the DeepSeek V3.2 vs Kimi K2.5 comparison based on?

66 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 K2.5'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/deepseek-v3-2-vs-kimi-k2-5" title="DeepSeek V3.2 vs Kimi K2.5, 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/deepseek-v3-2-vs-kimi-k2-5">LLMBenchmark.ai, DeepSeek V3.2 vs Kimi K2.5</a></p>