Enter opens the highlighted result. Esc closes.

DeepSeek V4 Pro 0423 vs Kimi K3

Kimi K3 leads DeepSeek V4 Pro 0423 on coding, 62.3 to 38.7 on the Vibe Coding Index, and DeepSeek V4 Pro 0423 costs 5.8x less per output token ($2.60 vs $15.00 per million). Updated October 22, 2026; 82 benchmarks have a result for both.

Replace DeepSeek V4 Pro 0423 Replace Kimi K3
DeepSeek V4 Pro 0423DeepSeek
Coding
38.7
Overall
50.0
Output $/M
$2.60
3
Kimi K3Moonshot AI
Coding
62.3
Overall
66.5
Output $/M
$15.00
79
vs boards won of 82 shared

DeepSeek V4 Pro 0423 or Kimi K3: which to pick

Pick Kimi K3 for coding: it scores 62.3 on the Vibe Coding Index against 38.7 for DeepSeek V4 Pro 0423.

Pick DeepSeek V4 Pro 0423 for output tokens 5.8x cheaper ($2.60 vs $15.00 per million) and a lower cost per solved task ($0.57 against $0.81).

Model ADeepSeek V4 Pro 0423DeepSeek38.7/1005 independent benchmarks$0.57 per solved taskModel BKimi K3Moonshot AI62.3/1006 independent benchmarks$0.81 per solved task
Shared results
82
DeepSeek V4 Pro 0423 only
7
Kimi K3 only
40
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 V4 Pro 0423 38.7 from 5 benchmarks, Kimi K3 62.3 from 6 benchmarks.
Widest category
Math, 24.8 points apart on average over 7 shared benchmarks.
Widest single gap
ProofBench: DeepSeek V4 Pro 0423 16.0% against Kimi K3 87.0%, 71.0 points apart on a 0 to 100 scale.
Output price
DeepSeek V4 Pro 0423 $2.60 against Kimi K3 $15.00 per million output tokens, 5.8x apart.
Context window
Both take 1.05M tokens.

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 V4 Pro 0423BarsKimi K3Ties
Coding214
Intelligence02
Agentic work09
Reasoning08
Math07
Knowledge010
Web design07
General122
All shared boards379
CodingLike-for-likeSix of these boards feed the Vibe Coding Index214
Coding benchmarks for DeepSeek V4 Pro 0423 and Kimi K3
BenchmarkDeepSeek V4 Pro 0423Kimi K3Leader
LiveBench codingNot measured59.3%Only Kimi K3 measured
LMArena WebDev14471655Kimi K3
AA Coding Index59.476.2Kimi K3
LiveCodeBench (Vals AI)87.5%87.2%DeepSeek V4 Pro 0423
SWE-bench Verified (Vals AI)77.4%93.4%Kimi K3
Terminal-Bench 4 (Vals AI)11.1%17.2%Kimi K3
Vibe Code Bench (Vals AI)49.9%85.0%Kimi K3
Code migration (Vals AI)26.2%16.1%DeepSeek V4 Pro 0423
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)50.2%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)51.3%Not measuredOnly DeepSeek V4 Pro 0423 measured
CyberBench (Vals AI)Not measured75.2%Only Kimi K3 measured
SciCodeNot measured59.5%Only Kimi K3 measured
FrontierCode17.6%44.2%Kimi K3
FrontierSWENot measured25.9%Only Kimi K3 measured
WeirdML48.9%82.6%Kimi K3
ALE-Bench1006.11524.5Kimi K3
LMArena Text: coding14701508Kimi K3
LMArena Text: software and IT14691499Kimi K3
LMArena WebDev: React14411670Kimi K3
LMArena WebDev: HTML14351644Kimi K3
LMArena WebDev: from an imageNot measured1579Only Kimi K3 measured
SWE-Bench Pro V2Not measured97.7%Only Kimi K3 measured
SWE Atlas: Codebase QnA27.2%Not measuredOnly DeepSeek V4 Pro 0423 measured
SWE Atlas: Test Writing27.1%Not measuredOnly DeepSeek V4 Pro 0423 measured
Neither model has a result on the other 15 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index02
Intelligence benchmarks for DeepSeek V4 Pro 0423 and Kimi K3
BenchmarkDeepSeek V4 Pro 0423Kimi K3Leader
AA Intelligence Index30.443.6Kimi K3
Epoch Capabilities Index149.1157.9Kimi K3
Agentic workLike-for-likePublic boards, shown as published, kept out of the index09
Agentic work benchmarks for DeepSeek V4 Pro 0423 and Kimi K3
BenchmarkDeepSeek V4 Pro 0423Kimi K3Leader
AA Agentic Index26.350.0Kimi K3
Design Arena: agents building web apps10001295Kimi K3
Design Arena: agents building full-stack apps9481315Kimi K3
Design Arena: agents building mobile appsNot measured1268Only Kimi K3 measured
Design Arena: agents building Android appsNot measured1252Only Kimi K3 measured
Design Arena: agents building Godot games10591223Kimi K3
Design Arena: agents building gamesNot measured1252Only Kimi K3 measured
Design Arena: HTML slidesNot measured1196Only Kimi K3 measured
Design Arena: PowerPoint slidesNot measured1245Only Kimi K3 measured
Design Arena: spreadsheetsNot measured1096Only 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)44.1%53.1%Kimi K3
Tax Agent Bench (Vals AI)25.2%33.4%Kimi K3
Legal Research Bench (Vals AI)23.1%46.1%Kimi K3
Harvey's Legal Agent Benchmark (Vals AI)Not measured12.9%Only Kimi K3 measured
Excel Modeling Benchmark (Vals AI)51.6%66.7%Kimi K3
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
APEX-AgentsNot measured47.8%Only Kimi K3 measured
PostTrainBenchNot measured32.0%Only Kimi K3 measured
Vending-Bench 2$3,285$5,165Kimi K3
MCP AtlasNot measured82.3%Only Kimi K3 measured
Neither model has a result on the other 17 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index08
Reasoning benchmarks for DeepSeek V4 Pro 0423 and Kimi K3
BenchmarkDeepSeek V4 Pro 0423Kimi K3Leader
GPQA Diamond89.4%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)Not measured93.5%Only Kimi K3 measured
Humanity's Last Exam (Artificial Analysis run)Not measured46.9%Only Kimi K3 measured
GPQA Diamond (Epoch AI run)90.9%93.1%Kimi K3
ARC-AGINot measured94.5%Only Kimi K3 measured
ARC-AGI-2Not measured60.4%Only Kimi K3 measured
SimpleBenchNot measured60.7%Only Kimi K3 measured
Chess puzzles19.0%37.0%Kimi K3
Mystery game puzzles17.0%26.0%Kimi K3
LMArena Text: hard prompts14611495Kimi K3
LMArena Text: expert14631520Kimi K3
LMArena Text: hard prompts in English14661496Kimi K3
Kagi LLM Benchmark53.5%Not measuredOnly DeepSeek V4 Pro 0423 measured
Humanity's Last Exam (Scale run)13.4%22.2%Kimi K3
Neither model has a result on the other 7 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index07
Math benchmarks for DeepSeek V4 Pro 0423 and Kimi K3
BenchmarkDeepSeek V4 Pro 0423Kimi K3Leader
OTIS Mock AIME96.7%97.2%Kimi K3
FrontierMath, tiers 1 to 345.3%72.2%Kimi K3
FrontierMath, tier 42.4%39.0%Kimi K3
ProofBench16.0%87.0%Kimi K3
LMArena Text: math14431494Kimi K3
LMArena Text: mathematical work14551505Kimi K3
MathArena26.2%48.0%Kimi K3
Neither model has a result on the other 7 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index010
Knowledge benchmarks for DeepSeek V4 Pro 0423 and Kimi K3
BenchmarkDeepSeek V4 Pro 0423Kimi K3Leader
MMLU Pro87.3%88.0%Kimi K3
LegalBench (Vals AI)80.3%86.2%Kimi K3
CaseLaw (Vals AI)59.4%Not measuredOnly DeepSeek V4 Pro 0423 measured
CorpFin (Vals AI)61.4%71.6%Kimi K3
TaxEval (Vals AI)72.1%75.7%Kimi K3
MortgageTax (Vals AI)Not measured66.3%Only Kimi K3 measured
MedCode (Vals AI)40.5%49.4%Kimi K3
SimpleQA Verified47.0%50.6%Kimi K3
LMArena Text: science14701508Kimi K3
LMArena Text: medicine and healthcare14661489Kimi K3
LMArena Text: legal and government14641503Kimi K3
LMArena Text: business and finance14431470Kimi K3
Neither model has a result on the other 8 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index07
Web design benchmarks for DeepSeek V4 Pro 0423 and Kimi K3
BenchmarkDeepSeek V4 Pro 0423Kimi K3Leader
Design Arena: websites12341335Kimi K3
Design Arena: UI components12191340Kimi K3
Design Arena: game dev12281360Kimi K3
Design Arena: data viz12031352Kimi K3
Design Arena: 3D12531387Kimi K3
Design Arena: all code categories12401360Kimi K3
Design Arena: SVG11391301Kimi K3
Design Arena: ASCII art1149Not measuredOnly DeepSeek V4 Pro 0423 measured
LiveBench designNot measured77.2%Only Kimi K3 measured
GeneralLike-for-likePublic boards, shown as published, kept out of the index122
General benchmarks for DeepSeek V4 Pro 0423 and Kimi K3
BenchmarkDeepSeek V4 Pro 0423Kimi K3Leader
Vals IndexNot measured53.0%Only Kimi K3 measured
LiveBench data analysisNot measured78.7%Only Kimi K3 measured
Public Benefits Bench (Vals AI)62.9%68.2%Kimi K3
SAGE (Vals AI)Not measured52.8%Only Kimi K3 measured
MedScribe (Vals AI)75.1%88.0%Kimi K3
Vals Multimodal IndexNot measured73.4%Only Kimi K3 measured
Long context reasoning (AA-LCR)Not measured88.7%Only Kimi K3 measured
DTBench90.7%91.2%Kimi K3
LMCA41.2%52.7%Kimi K3
Surface Evolver Bench40.0%95.0%Kimi K3
Furniture assemblyNot measured34.2%Only Kimi K3 measured
CL-bench Life13.5%Not measuredOnly DeepSeek V4 Pro 0423 measured
LMArena Text14511476Kimi K3
LMArena Text: instruction following14451485Kimi K3
LMArena Text: creative writing14461457Kimi K3
LMArena Text: English14591481Kimi K3
LMArena Text: non-English14391466Kimi K3
LMArena Text: Chinese14811529Kimi K3
LMArena Text: German14581490Kimi K3
LMArena Text: Japanese14461494Kimi K3
LMArena Text: Korean14091460Kimi K3
LMArena Text: French14731492Kimi K3
LMArena Text: Spanish14571472Kimi K3
LMArena Text: Russian14531485Kimi K3
LMArena Text: Polish14611458DeepSeek V4 Pro 0423
LMArena Text: multi-turn14681489Kimi K3
LMArena Text: longer queries14581494Kimi K3
LMArena Text: writing and language14471471Kimi K3
LMArena Text: entertainment and media14311453Kimi K3
EQ-Bench 411661339Kimi K3
Neither model has a result on the other 18 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for DeepSeek V4 Pro 0423 and Kimi K3
BenchmarkDeepSeek V4 Pro 0423Kimi 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 V4 Pro 0423$0.0026Fits in one request
Kimi K3$0.011Fits in one request

DeepSeek V4 Pro 0423 costs less

Repository review

50K input + 3K output tokens

DeepSeek V4 Pro 0423$0.073Fits in one request
Kimi K3$0.195Fits in one request

DeepSeek V4 Pro 0423 costs less

Agent loop

200K input + 10K output tokens

DeepSeek V4 Pro 0423$0.286Fits in one request
Kimi K3$0.750Fits in one request

DeepSeek V4 Pro 0423 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 V4 Pro 0423 and Kimi K3
SpecificationDeepSeek V4 Pro 0423MoonshotAI Kimi K3
MakerDeepSeekMoonshot AI
WeightsOpen weightsOpen weights
ReleasedApril 24, 2026July 16, 2026
Context window1.05M1.05M
Input $/Mtok$1.30$3.00
Output $/Mtok$2.60$15.00
Coding index38.762.3
Independent measurements behind it56
Cost per solved task$0.57$0.81
SourceOpenRouter listingOpenRouter listing

Questions

Is DeepSeek V4 Pro 0423 better than Kimi K3 for coding?

Pick Kimi K3 for coding: it scores 62.3 on the Vibe Coding Index against 38.7 for DeepSeek V4 Pro 0423. Pick DeepSeek V4 Pro 0423 for output tokens 5.8x cheaper ($2.60 vs $15.00 per million) and a lower cost per solved task ($0.57 against $0.81).

Which is cheaper, DeepSeek V4 Pro 0423 or Kimi K3?

DeepSeek V4 Pro 0423 costs $1.30 per million input tokens and $2.60 per million output tokens; Kimi K3 costs $3.00 and $15.00. Per solved SWE-bench Verified task, DeepSeek V4 Pro 0423 costs $0.57 and Kimi K3 $0.81.

Which has the bigger context window, DeepSeek V4 Pro 0423 or Kimi K3?

Neither: both take 1.05M tokens.

How many benchmarks is the DeepSeek V4 Pro 0423 vs Kimi K3 comparison based on?

82 benchmarks have a result for both models as of October 22, 2026. DeepSeek V4 Pro 0423's coding index rests on 5 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-v4-pro-vs-kimi-k3" title="DeepSeek V4 Pro 0423 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-v4-pro-vs-kimi-k3">LLMBenchmark.ai, DeepSeek V4 Pro 0423 vs Kimi K3</a></p>