Enter opens the highlighted result. Esc closes.

Claude Haiku 4.5 vs Kimi K3

Kimi K3 leads Claude Haiku 4.5 on coding, 62.3 to 35.6 on the Vibe Coding Index, and Claude Haiku 4.5 costs 3.0x less per output token ($5.00 vs $15.00 per million). Updated October 22, 2026; 81 benchmarks have a result for both.

Replace Claude Haiku 4.5 Replace Kimi K3
Claude Haiku 4.5Anthropic
Coding
35.6
Overall
41.0
Output $/M
$5.00
1
Kimi K3Moonshot AI
Coding
62.3
Overall
66.5
Output $/M
$15.00
80
vs boards won of 81 shared

Claude Haiku 4.5 or Kimi K3: which to pick

Pick Kimi K3 for coding: it scores 62.3 on the Vibe Coding Index against 35.6 for Claude Haiku 4.5.

Pick Claude Haiku 4.5 for output tokens 3.0x cheaper ($5.00 vs $15.00 per million) and a lower cost per solved task ($0.56 against $0.81).

Model AClaude Haiku 4.5Anthropic35.6/1004 independent benchmarks$0.56 per solved taskModel BKimi K3Moonshot AI62.3/1006 independent benchmarks$0.81 per solved task
Shared results
81
Claude Haiku 4.5 only
14
Kimi K3 only
36
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
Claude Haiku 4.5 35.6 from 4 benchmarks, Kimi K3 62.3 from 6 benchmarks.
Widest category
Agentic work, 32.6 points apart on average over 9 shared benchmarks.
Widest single gap
Vibe Code Bench (Vals AI): Claude Haiku 4.5 11.4% against Kimi K3 85.0%, 73.6 points apart on a 0 to 100 scale.
Output price
Claude Haiku 4.5 $5.00 against Kimi K3 $15.00 per million output tokens, 3.0x apart.
Context window
Claude Haiku 4.5 takes 200K 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 Haiku 4.5BarsKimi K3Ties
Coding014
Intelligence02
Agentic work18
Reasoning010
Math03
Knowledge011
Web design08
General024
All shared boards180
CodingLike-for-likeSix of these boards feed the Vibe Coding Index014
Coding benchmarks for Claude Haiku 4.5 and Kimi K3
BenchmarkClaude Haiku 4.5Kimi K3Leader
SWE-bench Verified66.6%Not measuredOnly Claude Haiku 4.5 measured
SWE-bench Multilingual64.7%Not measuredOnly Claude Haiku 4.5 measured
LiveBench coding48.1%59.3%Kimi K3
LMArena WebDev13301655Kimi K3
AA Coding Index43.976.2Kimi K3
LiveCodeBench (Vals AI)41.2%87.2%Kimi K3
SWE-bench Verified (Vals AI)66.6%93.4%Kimi K3
Terminal-Bench 4 (Vals AI)Not measured17.2%Only Kimi K3 measured
Vibe Code Bench (Vals AI)11.4%85.0%Kimi K3
Code migration (Vals AI)7.5%16.1%Kimi K3
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)43.8%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
CyberBench (Vals AI)Not measured75.2%Only Kimi K3 measured
SciCodeNot measured59.5%Only Kimi K3 measured
Terminal-Bench35.5%Not measuredOnly Claude Haiku 4.5 measured
FrontierCodeNot measured44.2%Only Kimi K3 measured
FrontierSWENot measured25.9%Only Kimi K3 measured
WeirdML45.4%82.6%Kimi K3
ALE-BenchNot measured1524.5Only Kimi K3 measured
LMArena Text: coding14541508Kimi K3
LMArena Text: software and IT14391499Kimi K3
LMArena WebDev: React13261670Kimi K3
LMArena WebDev: HTML13181644Kimi K3
LMArena WebDev: from an imageNot measured1579Only Kimi K3 measured
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 Haiku 4.5 and Kimi K3
BenchmarkClaude Haiku 4.5Kimi K3Leader
AA Intelligence Index16.943.6Kimi K3
Epoch Capabilities Index142.2157.9Kimi K3
Agentic workLike-for-likePublic boards, shown as published, kept out of the index18
Agentic work benchmarks for Claude Haiku 4.5 and Kimi K3
BenchmarkClaude Haiku 4.5Kimi K3Leader
AA Agentic Index8.050.0Kimi K3
Design Arena: agents building web appsNot measured1295Only Kimi K3 measured
Design Arena: agents building full-stack appsNot measured1315Only Kimi K3 measured
Design Arena: agents building mobile appsNot measured1269Only Kimi K3 measured
Design Arena: agents building Android appsNot measured1253Only 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 measured1206Only Kimi K3 measured
Design Arena: PowerPoint slidesNot measured1247Only Kimi K3 measured
Design Arena: spreadsheetsNot measured1070Only Kimi K3 measured
LiveBench research42.2%79.0%Kimi K3
LiveBench browser40.0%16.0%Claude Haiku 4.5
LiveBench long agentic11.1%42.8%Kimi K3
Finance Agent (Vals AI)31.0%53.1%Kimi K3
Tax Agent Bench (Vals AI)5.9%33.4%Kimi K3
Legal Research Bench (Vals AI)10.6%46.1%Kimi K3
Harvey's Legal Agent Benchmark (Vals AI)Not measured12.9%Only Kimi K3 measured
Excel Modeling Benchmark (Vals AI)22.7%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
BALROG31.2%Not measuredOnly Claude Haiku 4.5 measured
DeepResearch Bench45.5%Not measuredOnly Claude Haiku 4.5 measured
PostTrainBenchNot measured32.0%Only Kimi K3 measured
Vending-Bench 2$459$5,165Kimi K3
Berkeley Function Calling Leaderboard (BFCL)68.7%Not measuredOnly Claude Haiku 4.5 measured
Neither model has a result on the other 14 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index010
Reasoning benchmarks for Claude Haiku 4.5 and Kimi K3
BenchmarkClaude Haiku 4.5Kimi K3Leader
GPQA Diamond72.2%92.9%Kimi K3
LiveBench reasoning61.7%90.7%Kimi K3
MMMU Pro (Vals AI)46.1%88.2%Kimi K3
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)71.2%93.1%Kimi K3
ARC-AGI47.7%94.5%Kimi K3
ARC-AGI-24.0%60.4%Kimi K3
SimpleBenchNot measured60.7%Only Kimi K3 measured
Chess puzzles8.0%37.0%Kimi K3
Mystery game puzzlesNot measured26.0%Only Kimi K3 measured
LMArena Text: hard prompts14211495Kimi K3
LMArena Text: expert14431520Kimi K3
LMArena Text: hard prompts in English14351496Kimi K3
Neither model has a result on the other 8 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index03
Math benchmarks for Claude Haiku 4.5 and Kimi K3
BenchmarkClaude Haiku 4.5Kimi K3Leader
AIME82.7%Not measuredOnly Claude Haiku 4.5 measured
MGSM (Vals AI)92.2%Not measuredOnly Claude Haiku 4.5 measured
OTIS Mock AIME66.7%97.2%Kimi K3
FrontierMath, tiers 1 to 3Not measured72.2%Only Kimi K3 measured
FrontierMath, tier 4Not measured39.0%Only Kimi K3 measured
ProofBenchNot measured87.0%Only Kimi K3 measured
MATH level 596.4%Not measuredOnly Claude Haiku 4.5 measured
LMArena Text: math13981494Kimi K3
LMArena Text: mathematical work14301505Kimi K3
Neither model has a result on the other 4 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index011
Knowledge benchmarks for Claude Haiku 4.5 and Kimi K3
BenchmarkClaude Haiku 4.5Kimi K3Leader
MMLU Pro78.7%88.0%Kimi K3
LegalBench (Vals AI)81.2%86.2%Kimi K3
CaseLaw (Vals AI)56.5%Not measuredOnly Claude Haiku 4.5 measured
CorpFin (Vals AI)60.6%71.6%Kimi K3
TaxEval (Vals AI)67.5%75.7%Kimi K3
MortgageTax (Vals AI)62.2%66.3%Kimi K3
MedQA (Vals AI)79.6%Not measuredOnly Claude Haiku 4.5 measured
MedCode (Vals AI)32.7%49.4%Kimi K3
SimpleQA Verified13.2%50.6%Kimi K3
LMArena Text: science14061508Kimi K3
LMArena Text: medicine and healthcare13941489Kimi K3
LMArena Text: legal and government14001503Kimi K3
LMArena Text: business and finance14001470Kimi K3
Neither model has a result on the other 5 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index08
Web design benchmarks for Claude Haiku 4.5 and Kimi K3
BenchmarkClaude Haiku 4.5Kimi K3Leader
Design Arena: websites11221334Kimi K3
Design Arena: UI components10971341Kimi K3
Design Arena: game dev10971358Kimi K3
Design Arena: data viz11241351Kimi K3
Design Arena: 3D10711387Kimi K3
Design Arena: all code categories11141360Kimi K3
Design Arena: SVG10251302Kimi K3
Design Arena: ASCII art1140Not measuredOnly Claude Haiku 4.5 measured
LiveBench design59.9%77.2%Kimi K3
GeneralLike-for-likePublic boards, shown as published, kept out of the index024
General benchmarks for Claude Haiku 4.5 and Kimi K3
BenchmarkClaude Haiku 4.5Kimi K3Leader
Vals IndexNot measured53.0%Only Kimi K3 measured
LiveBench data analysis59.3%78.7%Kimi K3
Public Benefits Bench (Vals AI)54.3%68.2%Kimi K3
SAGE (Vals AI)31.8%52.8%Kimi K3
MedScribe (Vals AI)85.2%88.0%Kimi K3
Vals Multimodal Index42.9%73.4%Kimi K3
Long context reasoning (AA-LCR)Not measured88.7%Only Kimi K3 measured
DTBench73.6%91.2%Kimi K3
LMCA30.9%52.7%Kimi K3
Surface Evolver BenchNot measured95.0%Only Kimi K3 measured
Furniture assemblyNot measured34.2%Only Kimi K3 measured
ExploitBench13.7%Not measuredOnly Claude Haiku 4.5 measured
LMArena Text13971476Kimi K3
LMArena Text: instruction following14141485Kimi K3
LMArena Text: creative writing13711457Kimi K3
LMArena Text: English14141481Kimi K3
LMArena Text: non-English13771466Kimi K3
LMArena Text: Chinese14181529Kimi K3
LMArena Text: German13741490Kimi K3
LMArena Text: Japanese13381494Kimi K3
LMArena Text: Korean13461460Kimi K3
LMArena Text: French14111492Kimi K3
LMArena Text: Spanish14211472Kimi K3
LMArena Text: Russian13811485Kimi K3
LMArena Text: Polish13431458Kimi K3
LMArena Text: multi-turn14091489Kimi K3
LMArena Text: longer queries14271494Kimi K3
LMArena Text: writing and language13861471Kimi K3
LMArena Text: entertainment and media13691453Kimi K3
LMArena Document1420Not measuredOnly Claude Haiku 4.5 measured
Neither model has a result on the other 16 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for Claude Haiku 4.5 and Kimi K3
BenchmarkClaude Haiku 4.5Kimi 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 Haiku 4.5$0.0035Fits in one request
Kimi K3$0.011Fits in one request

Claude Haiku 4.5 costs less

Repository review

50K input + 3K output tokens

Claude Haiku 4.5$0.065Fits in one request
Kimi K3$0.195Fits in one request

Claude Haiku 4.5 costs less

Agent loop

200K input + 10K output tokens

Claude Haiku 4.5$0.250Exceeds the context window
Kimi K3$0.750Fits in one request

Claude Haiku 4.5 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 Haiku 4.5 and Kimi K3
SpecificationAnthropic Claude Haiku 4.5MoonshotAI Kimi K3
MakerAnthropicMoonshot AI
WeightsNo public weights listedOpen weights
ReleasedOctober 15, 2025July 16, 2026
Context window200K1.05M
Input $/Mtok$1.00$3.00
Output $/Mtok$5.00$15.00
Coding index35.662.3
Independent measurements behind it46
Cost per solved task$0.56$0.81
SourceOpenRouter listingOpenRouter listing

Questions

Is Claude Haiku 4.5 better than Kimi K3 for coding?

Pick Kimi K3 for coding: it scores 62.3 on the Vibe Coding Index against 35.6 for Claude Haiku 4.5. Pick Claude Haiku 4.5 for output tokens 3.0x cheaper ($5.00 vs $15.00 per million) and a lower cost per solved task ($0.56 against $0.81).

Which is cheaper, Claude Haiku 4.5 or Kimi K3?

Claude Haiku 4.5 costs $1.00 per million input tokens and $5.00 per million output tokens; Kimi K3 costs $3.00 and $15.00. Per solved SWE-bench Verified task, Claude Haiku 4.5 costs $0.56 and Kimi K3 $0.81.

Which has the bigger context window, Claude Haiku 4.5 or Kimi K3?

Kimi K3, with 1.05M tokens against 200K.

How many benchmarks is the Claude Haiku 4.5 vs Kimi K3 comparison based on?

81 benchmarks have a result for both models as of October 22, 2026. Claude Haiku 4.5's coding index rests on 4 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/claude-haiku-4-5-vs-kimi-k3" title="Claude Haiku 4.5 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-haiku-4-5-vs-kimi-k3">LLMBenchmark.ai, Claude Haiku 4.5 vs Kimi K3</a></p>