LLMBenchmark.ai

Enter opens the highlighted result. Esc closes.

Claude Sonnet 5 vs Kimi K3

Updated October 21, 2026. 107 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.

Replace Claude Sonnet 5 Replace Kimi K3
Claude Sonnet 5Anthropic
Coding
63.5
Overall
38.2
Output $/M
$10.00
14
Kimi K3Moonshot AI
Coding
61.8
Overall
43.6
Output $/M
$11.936
93
vs boards won of 107 shared

Decision reading

Claude Sonnet 5 and Kimi K3 are level for coding, 63.5 against 61.8 on the Vibe Coding Index, so price and context decide.

Pick Kimi K3 when a solved task costs $0.81 against $1.87, or when the context window is larger, 1.05M against 1M tokens. Pick Claude Sonnet 5 when output tokens cost 1.2x less, or when what matters is LiveBench coding or Code migration (Vals AI), where it leads.

Model AClaude Sonnet 5Anthropic63.5/1002 independent benchmarks$1.87 per solved taskModel BKimi K3Moonshot AI61.8/1002 independent benchmarks$0.81 per solved task
Shared results
107
Claude Sonnet 5 only
13
Kimi K3 only
10
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 5 63.5 from 2 benchmarks, Kimi K3 61.8 from 2 benchmarks.
Widest category
Web design, 10.4 points apart on average over 8 shared benchmarks.
Widest single gap
LiveBench browser: Claude Sonnet 5 72.0% against Kimi K3 16.0%, 56.0 points apart on a 0 to 100 scale.
Output price
Claude Sonnet 5 $10.00 against Kimi K3 $11.936 per million output tokens, 1.2x apart.
Context window
Claude Sonnet 5 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 5BarsKimi K3Ties
Coding220
Intelligence02
Agentic work713
Reasoning210
Math06
Knowledge110
Web design17
General125
All shared boards1493
CodingLike-for-likeFour of these boards feed the Vibe Coding Index220
Coding benchmarks for Claude Sonnet 5 and Kimi K3
BenchmarkClaude Sonnet 5Kimi K3Leader
LiveBench coding74.7%59.3%Claude Sonnet 5
LMArena WebDev15401655Kimi K3
AA Coding Index71.576.2Kimi K3
LiveCodeBench (Vals AI)82.4%87.2%Kimi K3
SWE-bench Verified (Vals AI)79.6%93.4%Kimi K3
Terminal-Bench 4 (Vals AI)10.6%17.2%Kimi K3
Vibe Code Bench (Vals AI)81.3%85.0%Kimi K3
Code migration (Vals AI)44.4%16.1%Claude Sonnet 5
ProgramBench (Vals AI)0.0%2.0%Kimi K3
IOI (Vals AI)45.0%48.9%Kimi K3
Terminal-Bench 2.1 (Vals AI)74.5%80.9%Kimi K3
SWE-bench Multimodal (Vals AI)Not measured44.2%Only Kimi K3 measured
Vibe Code Bench 1-100 (Vals AI)13.8%18.2%Kimi K3
SkillsBench (Vals AI)46.5%Not measuredOnly Claude Sonnet 5 measured
CyberBench (Vals AI)70.3%75.2%Kimi K3
SciCode54.3%59.5%Kimi K3
FrontierCode42.7%44.2%Kimi K3
FrontierSWENot measured25.9%Only Kimi K3 measured
GSO-Bench37.3%Not measuredOnly Claude Sonnet 5 measured
WeirdML68.8%82.6%Kimi K3
ALE-Bench1463.11524.5Kimi K3
LMArena Text: coding14831508Kimi K3
LMArena Text: software and IT14741499Kimi K3
LMArena WebDev: React15411670Kimi K3
LMArena WebDev: HTML15271644Kimi K3
LMArena WebDev: from an image15401579Kimi K3
Neither model has a result on the other 12 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index02
Intelligence benchmarks for Claude Sonnet 5 and Kimi K3
BenchmarkClaude Sonnet 5Kimi K3Leader
AA Intelligence Index38.243.6Kimi K3
Epoch Capabilities Index156.9157.9Kimi K3
Agentic workLike-for-likePublic boards, shown as published, kept out of the index713
Agentic work benchmarks for Claude Sonnet 5 and Kimi K3
BenchmarkClaude Sonnet 5Kimi K3Leader
AA Agentic Index43.650.0Kimi K3
Design Arena: agents building web apps12451296Kimi K3
Design Arena: agents building full-stack apps12491315Kimi K3
Design Arena: agents building mobile apps12151267Kimi K3
Design Arena: agents building Android apps12311256Kimi K3
Design Arena: agents building Godot games12251223Claude Sonnet 5
Design Arena: agents building games12271252Kimi K3
Design Arena: HTML slides12181256Kimi K3
Design Arena: PowerPoint slides12161273Kimi K3
Design Arena: spreadsheets10041058Kimi K3
LiveBench research82.8%79.0%Claude Sonnet 5
LiveBench browser72.0%16.0%Claude Sonnet 5
LiveBench long agentic39.0%42.8%Kimi K3
SREBench (Vals AI)0.4%Not measuredOnly Claude Sonnet 5 measured
Finance Agent (Vals AI)53.9%53.1%Claude Sonnet 5
Tax Agent Bench (Vals AI)29.4%33.4%Kimi K3
Legal Research Bench (Vals AI)41.8%46.1%Kimi K3
Harvey's Legal Agent Benchmark (Vals AI)Not measured12.9%Only Kimi K3 measured
Excel Modeling Benchmark (Vals AI)66.3%66.7%Kimi K3
BioMysteryBench (Vals AI)Not measured72.6%Only Kimi K3 measured
Terminal-Bench-Science (Vals AI)5.7%1.4%Claude Sonnet 5
Time Horizon Index (Vals AI)Not measured10.5%Only Kimi K3 measured
APEX-Agents54.5%47.8%Claude Sonnet 5
PostTrainBenchNot measured32.0%Only Kimi K3 measured
Vending-Bench 2$6,378$5,165Claude Sonnet 5
Neither model has a result on the other 14 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index210
Reasoning benchmarks for Claude Sonnet 5 and Kimi K3
BenchmarkClaude Sonnet 5Kimi K3Leader
GPQA Diamond88.9%92.9%Kimi K3
LiveBench reasoning88.7%90.7%Kimi K3
MMMU Pro (Vals AI)83.0%88.2%Kimi K3
GPQA Diamond (Artificial Analysis run)91.1%93.5%Kimi K3
Humanity's Last Exam (Artificial Analysis run)41.3%46.9%Kimi K3
GPQA Diamond (Epoch AI run)90.5%93.1%Kimi K3
ARC-AGINot measured94.5%Only Kimi K3 measured
ARC-AGI-2Not measured60.4%Only Kimi K3 measured
SimpleBench60.6%60.7%Kimi K3
Chess puzzles45.0%37.0%Claude Sonnet 5
Mystery game puzzles35.0%26.0%Claude Sonnet 5
LMArena Text: hard prompts14611495Kimi K3
LMArena Text: expert14891520Kimi K3
LMArena Text: hard prompts in English14641496Kimi K3
LMArena Vision: diagrams1293Not measuredOnly Claude Sonnet 5 measured
LMArena Vision: homework1311Not measuredOnly Claude Sonnet 5 measured
Neither model has a result on the other 5 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index06
Math benchmarks for Claude Sonnet 5 and Kimi K3
BenchmarkClaude Sonnet 5Kimi K3Leader
OTIS Mock AIME94.7%97.2%Kimi K3
FrontierMath, tiers 1 to 365.6%72.2%Kimi K3
FrontierMath, tier 429.3%39.0%Kimi K3
ProofBench77.0%87.0%Kimi K3
LMArena Text: math14671494Kimi K3
LMArena Text: mathematical work14811505Kimi K3
Neither model has a result on the other 7 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index110
Knowledge benchmarks for Claude Sonnet 5 and Kimi K3
BenchmarkClaude Sonnet 5Kimi K3Leader
MMLU Pro87.5%88.0%Kimi K3
LegalBench (Vals AI)83.9%86.2%Kimi K3
CorpFin (Vals AI)67.0%71.6%Kimi K3
TaxEval (Vals AI)75.6%75.7%Kimi K3
MortgageTax (Vals AI)70.0%66.3%Claude Sonnet 5
MedCode (Vals AI)47.5%49.4%Kimi K3
SimpleQA Verified33.7%50.6%Kimi K3
LMArena Text: science14601508Kimi K3
LMArena Text: medicine and healthcare14421489Kimi K3
LMArena Text: legal and government14541503Kimi K3
LMArena Text: business and finance14361470Kimi K3
Neither model has a result on the other 6 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index17
Web design benchmarks for Claude Sonnet 5 and Kimi K3
BenchmarkClaude Sonnet 5Kimi K3Leader
Design Arena: websites12741336Kimi K3
Design Arena: UI components12791345Kimi K3
Design Arena: game dev12781361Kimi K3
Design Arena: data viz12511350Kimi K3
Design Arena: 3D12611388Kimi K3
Design Arena: all code categories12761361Kimi K3
Design Arena: SVG11931301Kimi K3
Design Arena: ASCII art1207Not measuredOnly Claude Sonnet 5 measured
LiveBench design82.0%77.2%Claude Sonnet 5
GeneralLike-for-likePublic boards, shown as published, kept out of the index125
General benchmarks for Claude Sonnet 5 and Kimi K3
BenchmarkClaude Sonnet 5Kimi K3Leader
Vals IndexNot measured53.0%Only Kimi K3 measured
LiveBench data analysis71.7%78.7%Kimi K3
Public Benefits Bench (Vals AI)66.0%68.2%Kimi K3
SAGE (Vals AI)48.9%52.8%Kimi K3
MedScribe (Vals AI)76.0%88.0%Kimi K3
Vals Multimodal Index68.8%73.4%Kimi K3
Long context reasoning (AA-LCR)82.0%88.7%Kimi K3
DTBench92.5%91.2%Claude Sonnet 5
LMCA50.0%52.7%Kimi K3
Surface Evolver Bench60.0%95.0%Kimi K3
Furniture assemblyNot measured34.2%Only Kimi K3 measured
LMArena Text14421476Kimi K3
LMArena Text: instruction following14521485Kimi K3
LMArena Text: creative writing14161457Kimi K3
LMArena Vision1273Not measuredOnly Claude Sonnet 5 measured
LMArena Text: English14501481Kimi K3
LMArena Text: non-English14311466Kimi K3
LMArena Text: Chinese14781529Kimi K3
LMArena Text: German14421490Kimi K3
LMArena Text: Japanese14221494Kimi K3
LMArena Text: Korean14121460Kimi K3
LMArena Text: French14631492Kimi K3
LMArena Text: Spanish14381472Kimi K3
LMArena Text: Russian14501485Kimi K3
LMArena Text: Polish14251458Kimi K3
LMArena Text: multi-turn14531489Kimi K3
LMArena Text: longer queries14621494Kimi K3
LMArena Text: writing and language14361471Kimi K3
LMArena Text: entertainment and media14111453Kimi K3
LMArena Vision: English1275Not measuredOnly Claude Sonnet 5 measured
LMArena Vision: Chinese1331Not measuredOnly Claude Sonnet 5 measured
LMArena Vision: reading text1288Not measuredOnly Claude Sonnet 5 measured
LMArena Vision: humor1261Not measuredOnly Claude Sonnet 5 measured
LMArena Vision: creative writing1246Not measuredOnly Claude Sonnet 5 measured
LMArena Document1466Not measuredOnly Claude Sonnet 5 measured
Neither model has a result on the other 11 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for Claude Sonnet 5 and Kimi K3
BenchmarkClaude Sonnet 5Kimi 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 5$0.0070Fits in one request
Kimi K3$0.0062Fits in one request

Kimi K3 costs less

Repository review

50K input + 3K output tokens

Claude Sonnet 5$0.130Fits in one request
Kimi K3$0.048Fits in one request

Kimi K3 costs less

Agent loop

200K input + 10K output tokens

Claude Sonnet 5$0.500Fits 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 5 and Kimi K3
SpecificationAnthropic Claude Sonnet 5MoonshotAI Kimi K3
MakerAnthropicMoonshot AI
WeightsNo public weights listedOpen weights
ReleasedJune 30, 2026July 16, 2026
Context window1M1.05M
Input $/Mtok$2.00$0.239
Output $/Mtok$10.00$11.936
Coding index63.561.8
Independent measurements behind it22
Cost per solved task$1.87$0.81
SourceOpenRouter listingOpenRouter listing

Questions

Is Claude Sonnet 5 better than Kimi K3 for coding?

Claude Sonnet 5 and Kimi K3 are level for coding, 63.5 against 61.8 on the Vibe Coding Index, so price and context decide. Pick Kimi K3 when a solved task costs $0.81 against $1.87, or when the context window is larger, 1.05M against 1M tokens. Pick Claude Sonnet 5 when output tokens cost 1.2x less, or when what matters is LiveBench coding or Code migration (Vals AI), where it leads.

Which is cheaper, Claude Sonnet 5 or Kimi K3?

Claude Sonnet 5 costs $2.00 per million input tokens and $10.00 per million output tokens; Kimi K3 costs $0.239 and $11.936. Per solved SWE-bench Verified task, Claude Sonnet 5 costs $1.87 and Kimi K3 $0.81.

Which has the bigger context window, Claude Sonnet 5 or Kimi K3?

Kimi K3, with 1.05M tokens against 1M.

How many benchmarks is the Claude Sonnet 5 vs Kimi K3 comparison based on?

107 benchmarks have a result for both models as of October 21, 2026. Claude Sonnet 5'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-5-vs-kimi-k3" title="Claude Sonnet 5 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-5-vs-kimi-k3">LLMBenchmark.ai, Claude Sonnet 5 vs Kimi K3</a></p>