Enter opens the highlighted result. Esc closes.

DeepSeek V4 Pro 0813 vs Kimi K3

Updated October 21, 2026. 76 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.

Replace DeepSeek V4 Pro 0813 Replace Kimi K3
DeepSeek V4 Pro 0813DeepSeek
Coding
54.6
Overall
36.0
Output $/M
$1.98
12
Kimi K3Moonshot AI
Coding
61.8
Overall
43.6
Output $/M
$11.936
64
vs boards won of 76 shared

Decision reading

Pick Kimi K3 for coding: it scores 61.8 on the Vibe Coding Index against 54.6 for DeepSeek V4 Pro 0813.

Pick DeepSeek V4 Pro 0813 when output tokens cost 6.0x less, or when a solved task costs $0.10 against $0.81.

Model ADeepSeek V4 Pro 0813DeepSeek54.6/1001 independent benchmark$0.10 per solved taskModel BKimi K3Moonshot AI61.8/1002 independent benchmarks$0.81 per solved task
Shared results
76
DeepSeek V4 Pro 0813 only
2
Kimi K3 only
41
Like-for-like categories
7 of 9

Shared results can support a head-to-head reading. Results only one model has describe coverage, not superiority.

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 0813 54.6 from 1 benchmark, Kimi K3 61.8 from 2 benchmarks.
Widest category
Math, 12.9 points apart on average over 6 shared benchmarks.
Widest single gap
ProofBench: DeepSeek V4 Pro 0813 50.0% against Kimi K3 87.0%, 37.0 points apart on a 0 to 100 scale.
Output price
DeepSeek V4 Pro 0813 $1.98 against Kimi K3 $11.936 per million output tokens, 6.0x 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 0813BarsKimi K3Ties
Coding416
Intelligence02
Agentic work17
Reasoning38
Math15
Knowledge19
General217
All shared boards1264
CodingLike-for-likeFour of these boards feed the Vibe Coding Index416
Coding benchmarks for DeepSeek V4 Pro 0813 and Kimi K3
BenchmarkDeepSeek V4 Pro 0813Kimi K3Leader
LiveBench codingNot measured59.3%Only Kimi K3 measured
LMArena WebDev15821655Kimi K3
AA Coding Index68.876.2Kimi K3
LiveCodeBench (Vals AI)87.5%87.2%DeepSeek V4 Pro 0813
SWE-bench Verified (Vals AI)96.4%93.4%DeepSeek V4 Pro 0813
Terminal-Bench 4 (Vals AI)14.1%17.2%Kimi K3
Vibe Code Bench (Vals AI)82.3%85.0%Kimi K3
Code migration (Vals AI)41.5%16.1%DeepSeek V4 Pro 0813
ProgramBench (Vals AI)0.0%2.0%Kimi K3
IOI (Vals AI)51.6%48.9%DeepSeek V4 Pro 0813
Terminal-Bench 2.1 (Vals AI)54.7%80.9%Kimi K3
SWE-bench Multimodal (Vals AI)Not measured44.2%Only Kimi K3 measured
Vibe Code Bench 1-100 (Vals AI)17.5%18.2%Kimi K3
SkillsBench (Vals AI)53.8%Not measuredOnly DeepSeek V4 Pro 0813 measured
CyberBench (Vals AI)72.9%75.2%Kimi K3
SciCode51.0%59.5%Kimi K3
FrontierCode28.5%44.2%Kimi K3
FrontierSWENot measured25.9%Only Kimi K3 measured
WeirdML66.2%82.6%Kimi K3
ALE-Bench1403.21524.5Kimi K3
LMArena Text: coding14691508Kimi K3
LMArena Text: software and IT14621499Kimi K3
LMArena WebDev: React15881670Kimi K3
LMArena WebDev: HTML15661644Kimi K3
LMArena WebDev: from an imageNot measured1579Only Kimi K3 measured
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 DeepSeek V4 Pro 0813 and Kimi K3
BenchmarkDeepSeek V4 Pro 0813Kimi K3Leader
AA Intelligence Index36.043.6Kimi K3
Epoch Capabilities Index155.6157.9Kimi K3
Agentic workLike-for-likePublic boards, shown as published, kept out of the index17
Agentic work benchmarks for DeepSeek V4 Pro 0813 and Kimi K3
BenchmarkDeepSeek V4 Pro 0813Kimi K3Leader
AA Agentic Index41.350.0Kimi K3
Design Arena: agents building web appsNot measured1296Only Kimi K3 measured
Design Arena: agents building full-stack appsNot measured1315Only Kimi K3 measured
Design Arena: agents building mobile appsNot measured1267Only Kimi K3 measured
Design Arena: agents building Android appsNot measured1256Only 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 measured1256Only Kimi K3 measured
Design Arena: PowerPoint slidesNot measured1273Only Kimi K3 measured
Design Arena: spreadsheetsNot measured1058Only 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
SREBench (Vals AI)1.9%Not measuredOnly DeepSeek V4 Pro 0813 measured
Finance Agent (Vals AI)50.4%53.1%Kimi K3
Tax Agent Bench (Vals AI)26.8%33.4%Kimi K3
Legal Research Bench (Vals AI)40.9%46.1%Kimi K3
Harvey's Legal Agent Benchmark (Vals AI)10.8%12.9%Kimi K3
Excel Modeling Benchmark (Vals AI)52.8%66.7%Kimi K3
BioMysteryBench (Vals AI)Not measured72.6%Only Kimi K3 measured
Terminal-Bench-Science (Vals AI)4.3%1.4%DeepSeek V4 Pro 0813
Time Horizon Index (Vals AI)Not measured10.5%Only Kimi K3 measured
APEX-Agents47.3%47.8%Kimi K3
PostTrainBenchNot measured32.0%Only Kimi K3 measured
Vending-Bench 2Not measured$5,165Only Kimi K3 measured
Neither model has a result on the other 14 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index38
Reasoning benchmarks for DeepSeek V4 Pro 0813 and Kimi K3
BenchmarkDeepSeek V4 Pro 0813Kimi K3Leader
GPQA Diamond92.4%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)92.8%93.5%Kimi K3
Humanity's Last Exam (Artificial Analysis run)41.0%46.9%Kimi K3
GPQA Diamond (Epoch AI run)91.7%93.1%Kimi K3
ARC-AGI90.5%94.5%Kimi K3
ARC-AGI-261.3%60.4%DeepSeek V4 Pro 0813
SimpleBenchNot measured60.7%Only Kimi K3 measured
Chess puzzles46.0%37.0%DeepSeek V4 Pro 0813
Mystery game puzzles43.0%26.0%DeepSeek V4 Pro 0813
LMArena Text: hard prompts14581495Kimi K3
LMArena Text: expert14591520Kimi K3
LMArena Text: hard prompts in English14631496Kimi K3
Neither model has a result on the other 7 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index15
Math benchmarks for DeepSeek V4 Pro 0813 and Kimi K3
BenchmarkDeepSeek V4 Pro 0813Kimi K3Leader
OTIS Mock AIME98.6%97.2%DeepSeek V4 Pro 0813
FrontierMath, tiers 1 to 364.6%72.2%Kimi K3
FrontierMath, tier 426.8%39.0%Kimi K3
ProofBench50.0%87.0%Kimi K3
LMArena Text: math14411494Kimi K3
LMArena Text: mathematical work14431505Kimi K3
Neither model has a result on the other 7 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index19
Knowledge benchmarks for DeepSeek V4 Pro 0813 and Kimi K3
BenchmarkDeepSeek V4 Pro 0813Kimi K3Leader
MMLU Pro87.0%88.0%Kimi K3
LegalBench (Vals AI)82.4%86.2%Kimi K3
CorpFin (Vals AI)65.4%71.6%Kimi K3
TaxEval (Vals AI)73.1%75.7%Kimi K3
MortgageTax (Vals AI)Not measured66.3%Only Kimi K3 measured
MedCode (Vals AI)42.5%49.4%Kimi K3
SimpleQA Verified52.9%50.6%DeepSeek V4 Pro 0813
LMArena Text: science14571508Kimi K3
LMArena Text: medicine and healthcare14461489Kimi K3
LMArena Text: legal and government14591503Kimi K3
LMArena Text: business and finance14421470Kimi K3
Neither model has a result on the other 6 boards here
Web designDirectional onlyPublic boards, shown as published, kept out of the index8 boards, none shared
Web design benchmarks for DeepSeek V4 Pro 0813 and Kimi K3
BenchmarkDeepSeek V4 Pro 0813Kimi K3Leader
Design Arena: websitesNot measured1336Only Kimi K3 measured
Design Arena: UI componentsNot measured1345Only Kimi K3 measured
Design Arena: game devNot measured1361Only Kimi K3 measured
Design Arena: data vizNot measured1350Only Kimi K3 measured
Design Arena: 3DNot measured1388Only Kimi K3 measured
Design Arena: all code categoriesNot measured1361Only Kimi K3 measured
Design Arena: SVGNot measured1301Only Kimi K3 measured
LiveBench designNot measured77.2%Only Kimi K3 measured
Neither model has a result on the other 1 board here
GeneralLike-for-likePublic boards, shown as published, kept out of the index217
General benchmarks for DeepSeek V4 Pro 0813 and Kimi K3
BenchmarkDeepSeek V4 Pro 0813Kimi K3Leader
Vals Index53.0%53.0%DeepSeek V4 Pro 0813
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)80.2%88.0%Kimi K3
Vals Multimodal IndexNot measured73.4%Only Kimi K3 measured
Long context reasoning (AA-LCR)80.3%88.7%Kimi K3
DTBench93.9%91.2%DeepSeek V4 Pro 0813
LMCA45.5%52.7%Kimi K3
Surface Evolver BenchNot measured95.0%Only Kimi K3 measured
Furniture assemblyNot measured34.2%Only Kimi K3 measured
LMArena Text14461476Kimi K3
LMArena Text: instruction following14481485Kimi K3
LMArena Text: creative writing14391457Kimi K3
LMArena Text: English14571481Kimi K3
LMArena Text: non-English14311466Kimi K3
LMArena Text: Chinese14811529Kimi K3
LMArena Text: GermanNot measured1490Only Kimi K3 measured
LMArena Text: JapaneseNot measured1494Only Kimi K3 measured
LMArena Text: Korean14491460Kimi K3
LMArena Text: French14461492Kimi K3
LMArena Text: Spanish14351472Kimi K3
LMArena Text: Russian14481485Kimi K3
LMArena Text: PolishNot measured1458Only Kimi K3 measured
LMArena Text: multi-turn14541489Kimi K3
LMArena Text: longer queries14581494Kimi K3
LMArena Text: writing and language14431471Kimi K3
LMArena Text: entertainment and media14241453Kimi 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 0813 and Kimi K3
BenchmarkDeepSeek V4 Pro 0813Kimi 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 0813$0.0016Fits in one request
Kimi K3$0.0062Fits in one request

DeepSeek V4 Pro 0813 costs less

Repository review

50K input + 3K output tokens

DeepSeek V4 Pro 0813$0.039Fits in one request
Kimi K3$0.048Fits in one request

DeepSeek V4 Pro 0813 costs less

Agent loop

200K input + 10K output tokens

DeepSeek V4 Pro 0813$0.152Fits in one request
Kimi K3$0.167Fits in one request

DeepSeek V4 Pro 0813 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 0813 and Kimi K3
SpecificationDeepSeek V4 Pro 0813MoonshotAI Kimi K3
MakerDeepSeekMoonshot AI
WeightsOpen weightsOpen weights
ReleasedAugust 12, 2026July 16, 2026
Context window1.05M1.05M
Input $/Mtok$0.66$0.239
Output $/Mtok$1.98$11.936
Coding index54.661.8
Independent measurements behind it12
Cost per solved task$0.10$0.81
SourceOpenRouter listingOpenRouter listing

Questions

Is DeepSeek V4 Pro 0813 better than Kimi K3 for coding?

Pick Kimi K3 for coding: it scores 61.8 on the Vibe Coding Index against 54.6 for DeepSeek V4 Pro 0813. Pick DeepSeek V4 Pro 0813 when output tokens cost 6.0x less, or when a solved task costs $0.10 against $0.81.

Which is cheaper, DeepSeek V4 Pro 0813 or Kimi K3?

DeepSeek V4 Pro 0813 costs $0.66 per million input tokens and $1.98 per million output tokens; Kimi K3 costs $0.239 and $11.936. Per solved SWE-bench Verified task, DeepSeek V4 Pro 0813 costs $0.10 and Kimi K3 $0.81.

Which has the bigger context window, DeepSeek V4 Pro 0813 or Kimi K3?

Neither: both take 1.05M tokens.

How many benchmarks is the DeepSeek V4 Pro 0813 vs Kimi K3 comparison based on?

76 benchmarks have a result for both models as of October 21, 2026. DeepSeek V4 Pro 0813's coding index rests on 1 independent benchmark and Kimi K3's on 2. Where only one model has a result, the page says so instead of naming a winner.

Compare next