Enter opens the highlighted result. Esc closes.

Claude Sonnet 4.6 vs Kimi K3

Updated October 21, 2026. 94 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.

Replace Claude Sonnet 4.6 Replace Kimi K3
Claude Sonnet 4.6Anthropic
Coding
57.8
Overall
30.1
Output $/M
$15.00
8
Kimi K3Moonshot AI
Coding
61.8
Overall
43.6
Output $/M
$11.936
86
vs boards won of 94 shared

Decision reading

Pick Kimi K3 for coding: it scores 61.8 on the Vibe Coding Index against 57.8 for Claude Sonnet 4.6.

Pick Claude Sonnet 4.6 when what matters is LiveBench coding or Code migration (Vals AI), where it leads.

Model AClaude Sonnet 4.6Anthropic57.8/1002 independent benchmarks$1.68 per solved taskModel BKimi K3Moonshot AI61.8/1002 independent benchmarks$0.81 per solved task
Shared results
94
Claude Sonnet 4.6 only
23
Kimi K3 only
23
Like-for-like categories
8 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
Claude Sonnet 4.6 57.8 from 2 benchmarks, Kimi K3 61.8 from 2 benchmarks.
Widest category
Math, 15.6 points apart on average over 4 shared benchmarks.
Widest single gap
LiveBench browser: Claude Sonnet 4.6 68.0% against Kimi K3 16.0%, 52.0 points apart on a 0 to 100 scale.
Output price
Claude Sonnet 4.6 $15.00 against Kimi K3 $11.936 per million output tokens, 1.3x apart.
Context window
Claude Sonnet 4.6 takes 1M 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
CategoryClaude Sonnet 4.6BarsKimi K3Ties
Coding215
Intelligence02
Agentic work313
Reasoning112
Math04
Knowledge28
Web design08
General024
All shared boards886
CodingLike-for-likeFour of these boards feed the Vibe Coding Index215
Coding benchmarks for Claude Sonnet 4.6 and Kimi K3
BenchmarkClaude Sonnet 4.6Kimi K3Leader
LiveBench coding66.6%59.3%Claude Sonnet 4.6
LMArena WebDev15231655Kimi K3
AA Coding Index63.076.2Kimi K3
LiveCodeBench (Vals AI)82.1%87.2%Kimi K3
SWE-bench Verified (Vals AI)77.4%93.4%Kimi K3
Terminal-Bench 4 (Vals AI)Not measured17.2%Only Kimi K3 measured
Vibe Code Bench (Vals AI)55.8%85.0%Kimi K3
Code migration (Vals AI)39.9%16.1%Claude Sonnet 4.6
ProgramBench (Vals AI)0.5%2.0%Kimi K3
IOI (Vals AI)Not measured48.9%Only Kimi K3 measured
Terminal-Bench 2.1 (Vals AI)57.3%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)49.0%Not measuredOnly Claude Sonnet 4.6 measured
CyberBench (Vals AI)Not measured75.2%Only Kimi K3 measured
SciCode50.1%59.5%Kimi K3
Terminal-Bench Hard (Artificial Analysis run)53.0%Not measuredOnly Claude Sonnet 4.6 measured
Terminal-Bench53.4%Not measuredOnly Claude Sonnet 4.6 measured
FrontierCode24.3%44.2%Kimi K3
FrontierSWENot measured25.9%Only Kimi K3 measured
WeirdML66.1%82.6%Kimi K3
ALE-BenchNot measured1524.5Only Kimi K3 measured
LMArena Text: coding15031508Kimi K3
LMArena Text: software and IT14911499Kimi K3
LMArena WebDev: React15121670Kimi K3
LMArena WebDev: HTML15271644Kimi K3
LMArena WebDev: from an image15291579Kimi K3
Neither model has a result on the other 11 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index02
Intelligence benchmarks for Claude Sonnet 4.6 and Kimi K3
BenchmarkClaude Sonnet 4.6Kimi K3Leader
AA Intelligence Index30.143.6Kimi K3
Epoch Capabilities Index152.8157.9Kimi K3
Agentic workLike-for-likePublic boards, shown as published, kept out of the index313
Agentic work benchmarks for Claude Sonnet 4.6 and Kimi K3
BenchmarkClaude Sonnet 4.6Kimi K3Leader
AA Agentic Index31.850.0Kimi K3
Design Arena: agents building web apps11901296Kimi K3
Design Arena: agents building full-stack apps12131315Kimi K3
Design Arena: agents building mobile apps12121267Kimi K3
Design Arena: agents building Android apps12021256Kimi K3
Design Arena: agents building Godot games12261223Claude Sonnet 4.6
Design Arena: agents building games11771252Kimi K3
Design Arena: HTML slidesNot measured1256Only Kimi K3 measured
Design Arena: PowerPoint slidesNot measured1273Only Kimi K3 measured
Design Arena: spreadsheetsNot measured1058Only Kimi K3 measured
LiveBench research63.6%79.0%Kimi K3
LiveBench browser68.0%16.0%Claude Sonnet 4.6
LiveBench long agentic23.1%42.8%Kimi K3
Finance Agent (Vals AI)51.0%53.1%Kimi K3
Tax Agent Bench (Vals AI)25.8%33.4%Kimi K3
Legal Research Bench (Vals AI)38.5%46.1%Kimi K3
Harvey's Legal Agent Benchmark (Vals AI)Not measured12.9%Only Kimi K3 measured
Excel Modeling Benchmark (Vals AI)60.2%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
τ²-Bench Telecom79.5%Not measuredOnly Claude Sonnet 4.6 measured
APEX-Agents43.0%47.8%Kimi K3
OSWorld 2.09.3%Not measuredOnly Claude Sonnet 4.6 measured
DeepResearch Bench54.9%Not measuredOnly Claude Sonnet 4.6 measured
PostTrainBenchNot measured32.0%Only Kimi K3 measured
OSWorld72.1%Not measuredOnly Claude Sonnet 4.6 measured
Vending-Bench 2$7,204$5,165Claude Sonnet 4.6
Neither model has a result on the other 11 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index112
Reasoning benchmarks for Claude Sonnet 4.6 and Kimi K3
BenchmarkClaude Sonnet 4.6Kimi K3Leader
GPQA Diamond85.6%92.9%Kimi K3
LiveBench reasoning86.4%90.7%Kimi K3
MMMU Pro (Vals AI)83.6%88.2%Kimi K3
GPQA Diamond (Artificial Analysis run)87.5%93.5%Kimi K3
Humanity's Last Exam (Artificial Analysis run)33.6%46.9%Kimi K3
GPQA Diamond (Epoch AI run)87.4%93.1%Kimi K3
ARC-AGI86.5%94.5%Kimi K3
ARC-AGI-260.4%60.4%Claude Sonnet 4.6
SimpleBenchNot measured60.7%Only Kimi K3 measured
Chess puzzles23.0%37.0%Kimi K3
Mystery game puzzles16.0%26.0%Kimi K3
LMArena Text: hard prompts14851495Kimi K3
LMArena Text: expert15001520Kimi K3
LMArena Text: hard prompts in English14931496Kimi K3
LMArena Vision: diagrams1306Not measuredOnly Claude Sonnet 4.6 measured
LMArena Vision: homework1311Not measuredOnly Claude Sonnet 4.6 measured
Neither model has a result on the other 5 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index04
Math benchmarks for Claude Sonnet 4.6 and Kimi K3
BenchmarkClaude Sonnet 4.6Kimi K3Leader
AIME92.3%Not measuredOnly Claude Sonnet 4.6 measured
OTIS Mock AIME85.8%97.2%Kimi K3
FrontierMath, tiers 1 to 3Not measured72.2%Only Kimi K3 measured
FrontierMath, tier 4Not measured39.0%Only Kimi K3 measured
ProofBench45.0%87.0%Kimi K3
LMArena Text: math14621494Kimi K3
LMArena Text: mathematical work14831505Kimi K3
Neither model has a result on the other 6 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index28
Knowledge benchmarks for Claude Sonnet 4.6 and Kimi K3
BenchmarkClaude Sonnet 4.6Kimi K3Leader
MMLU Pro87.3%88.0%Kimi K3
LegalBench (Vals AI)82.1%86.2%Kimi K3
CaseLaw (Vals AI)64.0%Not measuredOnly Claude Sonnet 4.6 measured
CorpFin (Vals AI)65.3%71.6%Kimi K3
TaxEval (Vals AI)77.1%75.7%Claude Sonnet 4.6
MortgageTax (Vals AI)67.7%66.3%Claude Sonnet 4.6
MedQA (Vals AI)92.1%Not measuredOnly Claude Sonnet 4.6 measured
MedCode (Vals AI)Not measured49.4%Only Kimi K3 measured
SimpleQA Verified35.5%50.6%Kimi K3
LMArena Text: science14741508Kimi K3
LMArena Text: medicine and healthcare14511489Kimi K3
LMArena Text: legal and government14701503Kimi K3
LMArena Text: business and finance14641470Kimi K3
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 Claude Sonnet 4.6 and Kimi K3
BenchmarkClaude Sonnet 4.6Kimi K3Leader
Design Arena: websites12851336Kimi K3
Design Arena: UI components12711345Kimi K3
Design Arena: game dev12591361Kimi K3
Design Arena: data viz12781350Kimi K3
Design Arena: 3D12341388Kimi K3
Design Arena: all code categories12761361Kimi K3
Design Arena: SVG11961301Kimi K3
Design Arena: ASCII art1235Not measuredOnly Claude Sonnet 4.6 measured
LiveBench design71.8%77.2%Kimi K3
GeneralLike-for-likePublic boards, shown as published, kept out of the index024
General benchmarks for Claude Sonnet 4.6 and Kimi K3
BenchmarkClaude Sonnet 4.6Kimi K3Leader
Vals IndexNot measured53.0%Only Kimi K3 measured
LiveBench data analysis76.1%78.7%Kimi K3
Public Benefits Bench (Vals AI)62.5%68.2%Kimi K3
SAGE (Vals AI)46.6%52.8%Kimi K3
MedScribe (Vals AI)Not measured88.0%Only Kimi K3 measured
Vals Multimodal Index60.6%73.4%Kimi K3
IFBench56.6%Not measuredOnly Claude Sonnet 4.6 measured
Long context reasoning (AA-LCR)80.0%88.7%Kimi K3
DTBench89.9%91.2%Kimi K3
LMCA46.5%52.7%Kimi K3
Surface Evolver BenchNot measured95.0%Only Kimi K3 measured
Furniture assemblyNot measured34.2%Only Kimi K3 measured
ExploitBench23.6%Not measuredOnly Claude Sonnet 4.6 measured
LMArena Text14581476Kimi K3
LMArena Text: instruction following14761485Kimi K3
LMArena Text: creative writing14351457Kimi K3
LMArena Vision1283Not measuredOnly Claude Sonnet 4.6 measured
LMArena Text: English14721481Kimi K3
LMArena Text: non-English14401466Kimi K3
LMArena Text: Chinese14911529Kimi K3
LMArena Text: German14281490Kimi K3
LMArena Text: Japanese14201494Kimi K3
LMArena Text: Korean14101460Kimi K3
LMArena Text: French14651492Kimi K3
LMArena Text: Spanish14641472Kimi K3
LMArena Text: Russian14401485Kimi K3
LMArena Text: Polish14431458Kimi K3
LMArena Text: multi-turn14641489Kimi K3
LMArena Text: longer queries14791494Kimi K3
LMArena Text: writing and language14441471Kimi K3
LMArena Text: entertainment and media14311453Kimi K3
LMArena Vision: English1298Not measuredOnly Claude Sonnet 4.6 measured
LMArena Vision: Chinese1307Not measuredOnly Claude Sonnet 4.6 measured
LMArena Vision: reading text1296Not measuredOnly Claude Sonnet 4.6 measured
LMArena Vision: humor1248Not measuredOnly Claude Sonnet 4.6 measured
LMArena Vision: recognizing things1195Not measuredOnly Claude Sonnet 4.6 measured
LMArena Vision: creative writing1272Not measuredOnly Claude Sonnet 4.6 measured
LMArena Document1482Not measuredOnly Claude Sonnet 4.6 measured
Neither model has a result on the other 8 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for Claude Sonnet 4.6 and Kimi K3
BenchmarkClaude Sonnet 4.6Kimi 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

Claude Sonnet 4.6$0.011Fits in one request
Kimi K3$0.0062Fits in one request

Kimi K3 costs less

Repository review

50K input + 3K output tokens

Claude Sonnet 4.6$0.195Fits in one request
Kimi K3$0.048Fits in one request

Kimi K3 costs less

Agent loop

200K input + 10K output tokens

Claude Sonnet 4.6$0.750Fits in one request
Kimi K3$0.167Fits in one request

Kimi K3 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 Claude Sonnet 4.6 and Kimi K3
SpecificationAnthropic Claude Sonnet 4.6MoonshotAI Kimi K3
MakerAnthropicMoonshot AI
WeightsNo public weights listedOpen weights
ReleasedFebruary 17, 2026July 16, 2026
Context window1M1.05M
Input $/Mtok$3.00$0.239
Output $/Mtok$15.00$11.936
Coding index57.861.8
Independent measurements behind it22
Cost per solved task$1.68$0.81
SourceOpenRouter listingOpenRouter listing

Questions

Is Claude Sonnet 4.6 better than Kimi K3 for coding?

Pick Kimi K3 for coding: it scores 61.8 on the Vibe Coding Index against 57.8 for Claude Sonnet 4.6. Pick Claude Sonnet 4.6 when what matters is LiveBench coding or Code migration (Vals AI), where it leads.

Which is cheaper, Claude Sonnet 4.6 or Kimi K3?

Claude Sonnet 4.6 costs $3.00 per million input tokens and $15.00 per million output tokens; Kimi K3 costs $0.239 and $11.936. Per solved SWE-bench Verified task, Claude Sonnet 4.6 costs $1.68 and Kimi K3 $0.81.

Which has the bigger context window, Claude Sonnet 4.6 or Kimi K3?

Kimi K3, with 1.05M tokens against 1M.

How many benchmarks is the Claude Sonnet 4.6 vs Kimi K3 comparison based on?

94 benchmarks have a result for both models as of October 21, 2026. Claude Sonnet 4.6's coding index rests on 2 independent benchmarks and Kimi K3's on 2. 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/claude-sonnet-4-6-vs-kimi-k3" title="Claude Sonnet 4.6 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/claude-sonnet-4-6-vs-kimi-k3">LLMBenchmark.ai, Claude Sonnet 4.6 vs Kimi K3</a></p>