Enter opens the highlighted result. Esc closes.

Claude Haiku 4.5 vs Kimi K2.6

Kimi K2.6 leads Claude Haiku 4.5 on coding, 52.1 to 35.6 on the Vibe Coding Index, and Kimi K2.6 costs 1.3x less per output token ($4.00 vs $5.00 per million). Updated October 22, 2026; 76 benchmarks have a result for both.

Replace Claude Haiku 4.5 Replace Kimi K2.6
Claude Haiku 4.5Anthropic
Coding
35.6
Overall
41.0
Output $/M
$5.00
1
Kimi K2.6Moonshot AI
Coding
52.1
Overall
60.5
Output $/M
$4.00
74
vs boards won of 76 shared, 1 tied

Claude Haiku 4.5 or Kimi K2.6: which to pick

Pick Kimi K2.6 for coding: it scores 52.1 on the Vibe Coding Index against 35.6 for Claude Haiku 4.5, though on 3 benchmarks against 4.

Pick Claude Haiku 4.5 for work measured by MedScribe (Vals AI), where it leads.

Model AClaude Haiku 4.5Anthropic35.6/1004 independent benchmarks$0.56 per solved taskModel BKimi K2.6Moonshot AI52.1/1003 independent benchmarks$0.35 per solved task
Shared results
76
Claude Haiku 4.5 only
19
Kimi K2.6 only
33
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 K2.6 52.1 from 3 benchmarks.
Widest category
Agentic work, 18.2 points apart on average over 6 shared benchmarks.
Widest single gap
LiveCodeBench (Vals AI): Claude Haiku 4.5 41.2% against Kimi K2.6 86.8%, 45.6 points apart on a 0 to 100 scale.
Output price
Claude Haiku 4.5 $5.00 against Kimi K2.6 $4.00 per million output tokens, 1.3x apart.
Context window
Claude Haiku 4.5 takes 200K tokens, Kimi K2.6 262K.

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 K2.6Ties
Coding0121 tie
Intelligence02
Agentic work06
Reasoning07
Math03
Knowledge012
Web design08
General124
All shared boards1741 tie
CodingLike-for-likeSix of these boards feed the Vibe Coding Index012
Coding benchmarks for Claude Haiku 4.5 and Kimi K2.6
BenchmarkClaude Haiku 4.5Kimi K2.6Leader
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%Not measuredOnly Claude Haiku 4.5 measured
LMArena WebDev13301509Kimi K2.6
AA Coding Index43.961.8Kimi K2.6
LiveCodeBench (Vals AI)41.2%86.8%Kimi K2.6
SWE-bench Verified (Vals AI)66.6%76.2%Kimi K2.6
Vibe Code Bench (Vals AI)11.4%37.9%Kimi K2.6
Code migration (Vals AI)7.5%27.8%Kimi K2.6
ProgramBench (Vals AI)0.0%0.0%Tie
Terminal-Bench 2.1 (Vals AI)43.8%53.6%Kimi K2.6
SciCodeNot measured51.5%Only Kimi K2.6 measured
Terminal-Bench Hard (Artificial Analysis run)Not measured43.9%Only Kimi K2.6 measured
Terminal-Bench35.5%Not measuredOnly Claude Haiku 4.5 measured
WeirdML45.4%55.9%Kimi K2.6
ALE-BenchNot measured1092.7Only Kimi K2.6 measured
LMArena Text: coding14541489Kimi K2.6
LMArena Text: software and IT14391484Kimi K2.6
LMArena WebDev: React13261505Kimi K2.6
LMArena WebDev: HTML13181485Kimi K2.6
LMArena WebDev: from an imageNot measured1521Only Kimi K2.6 measured
Neither model has a result on the other 18 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index02
Intelligence benchmarks for Claude Haiku 4.5 and Kimi K2.6
BenchmarkClaude Haiku 4.5Kimi K2.6Leader
AA Intelligence Index16.927.0Kimi K2.6
Epoch Capabilities Index142.2150.9Kimi K2.6
Agentic workLike-for-likePublic boards, shown as published, kept out of the index06
Agentic work benchmarks for Claude Haiku 4.5 and Kimi K2.6
BenchmarkClaude Haiku 4.5Kimi K2.6Leader
AA Agentic Index8.020.5Kimi K2.6
Design Arena: agents building web appsNot measured1268Only Kimi K2.6 measured
Design Arena: agents building full-stack appsNot measured1155Only Kimi K2.6 measured
Design Arena: agents building mobile appsNot measured1156Only Kimi K2.6 measured
Design Arena: agents building Android appsNot measured1161Only Kimi K2.6 measured
Design Arena: agents building Godot gamesNot measured1120Only Kimi K2.6 measured
Design Arena: agents building gamesNot measured1141Only Kimi K2.6 measured
Design Arena: HTML slidesNot measured1135Only Kimi K2.6 measured
Design Arena: PowerPoint slidesNot measured1103Only Kimi K2.6 measured
Design Arena: spreadsheetsNot measured1276Only Kimi K2.6 measured
LiveBench research42.2%Not measuredOnly Claude Haiku 4.5 measured
LiveBench browser40.0%Not measuredOnly Claude Haiku 4.5 measured
LiveBench long agentic11.1%Not measuredOnly Claude Haiku 4.5 measured
Finance Agent (Vals AI)31.0%44.9%Kimi K2.6
Tax Agent Bench (Vals AI)5.9%12.4%Kimi K2.6
Legal Research Bench (Vals AI)10.6%15.9%Kimi K2.6
Excel Modeling Benchmark (Vals AI)22.7%57.9%Kimi K2.6
τ²-Bench TelecomNot measured95.9%Only Kimi K2.6 measured
OSWorld 2.0Not measured4.6%Only Kimi K2.6 measured
BALROG31.2%Not measuredOnly Claude Haiku 4.5 measured
DeepResearch Bench45.5%Not measuredOnly Claude Haiku 4.5 measured
Vending-Bench 2$459$6,205Kimi K2.6
Berkeley Function Calling Leaderboard (BFCL)68.7%Not measuredOnly Claude Haiku 4.5 measured
Neither model has a result on the other 18 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index07
Reasoning benchmarks for Claude Haiku 4.5 and Kimi K2.6
BenchmarkClaude Haiku 4.5Kimi K2.6Leader
GPQA Diamond72.2%89.1%Kimi K2.6
LiveBench reasoning61.7%Not measuredOnly Claude Haiku 4.5 measured
MMMU Pro (Vals AI)46.1%86.3%Kimi K2.6
GPQA Diamond (Artificial Analysis run)Not measured91.1%Only Kimi K2.6 measured
Humanity's Last Exam (Artificial Analysis run)Not measured37.5%Only Kimi K2.6 measured
GPQA Diamond (Epoch AI run)71.2%90.8%Kimi K2.6
ARC-AGI47.7%Not measuredOnly Claude Haiku 4.5 measured
ARC-AGI-24.0%Not measuredOnly Claude Haiku 4.5 measured
Chess puzzles8.0%20.0%Kimi K2.6
Mystery game puzzlesNot measured18.0%Only Kimi K2.6 measured
EBR-benchNot measured2.4%Only Kimi K2.6 measured
LMArena Text: hard prompts14211470Kimi K2.6
LMArena Text: expert14431491Kimi K2.6
LMArena Text: hard prompts in English14351471Kimi K2.6
LMArena Vision: diagramsNot measured1298Only Kimi K2.6 measured
LMArena Vision: homeworkNot measured1310Only Kimi K2.6 measured
Neither model has a result on the other 6 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index03
Math benchmarks for Claude Haiku 4.5 and Kimi K2.6
BenchmarkClaude Haiku 4.5Kimi K2.6Leader
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%96.1%Kimi K2.6
FrontierMath, tiers 1 to 3Not measured57.2%Only Kimi K2.6 measured
FrontierMath, tier 4Not measured25.6%Only Kimi K2.6 measured
ProofBenchNot measured16.0%Only Kimi K2.6 measured
MATH level 596.4%Not measuredOnly Claude Haiku 4.5 measured
LMArena Text: math13981474Kimi K2.6
LMArena Text: mathematical work14301480Kimi K2.6
Neither model has a result on the other 4 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index012
Knowledge benchmarks for Claude Haiku 4.5 and Kimi K2.6
BenchmarkClaude Haiku 4.5Kimi K2.6Leader
MMLU Pro78.7%87.6%Kimi K2.6
LegalBench (Vals AI)81.2%84.7%Kimi K2.6
CaseLaw (Vals AI)56.5%61.2%Kimi K2.6
CorpFin (Vals AI)60.6%66.7%Kimi K2.6
TaxEval (Vals AI)67.5%74.7%Kimi K2.6
MortgageTax (Vals AI)62.2%65.8%Kimi K2.6
MedQA (Vals AI)79.6%Not measuredOnly Claude Haiku 4.5 measured
MedCode (Vals AI)32.7%40.1%Kimi K2.6
SimpleQA Verified13.2%34.9%Kimi K2.6
LMArena Text: science14061468Kimi K2.6
LMArena Text: medicine and healthcare13941457Kimi K2.6
LMArena Text: legal and government14001462Kimi K2.6
LMArena Text: business and finance14001445Kimi K2.6
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 K2.6
BenchmarkClaude Haiku 4.5Kimi K2.6Leader
Design Arena: websites11221268Kimi K2.6
Design Arena: UI components10971263Kimi K2.6
Design Arena: game dev10971250Kimi K2.6
Design Arena: data viz11241249Kimi K2.6
Design Arena: 3D10711267Kimi K2.6
Design Arena: all code categories11141271Kimi K2.6
Design Arena: SVG10251181Kimi K2.6
Design Arena: ASCII art11401165Kimi K2.6
LiveBench design59.9%Not measuredOnly Claude Haiku 4.5 measured
GeneralLike-for-likePublic boards, shown as published, kept out of the index124
General benchmarks for Claude Haiku 4.5 and Kimi K2.6
BenchmarkClaude Haiku 4.5Kimi K2.6Leader
LiveBench data analysis59.3%Not measuredOnly Claude Haiku 4.5 measured
Public Benefits Bench (Vals AI)54.3%56.6%Kimi K2.6
SAGE (Vals AI)31.8%50.2%Kimi K2.6
MedScribe (Vals AI)85.2%78.2%Claude Haiku 4.5
Vals Multimodal Index42.9%56.4%Kimi K2.6
IFBenchNot measured76.0%Only Kimi K2.6 measured
Long context reasoning (AA-LCR)Not measured81.0%Only Kimi K2.6 measured
DTBench73.6%90.9%Kimi K2.6
LMCA30.9%37.3%Kimi K2.6
Furniture assemblyNot measured21.7%Only Kimi K2.6 measured
ExploitBench13.7%18.4%Kimi K2.6
LMArena Text13971455Kimi K2.6
LMArena Text: instruction following14141451Kimi K2.6
LMArena Text: creative writing13711434Kimi K2.6
LMArena VisionNot measured1282Only Kimi K2.6 measured
LMArena Text: English14141460Kimi K2.6
LMArena Text: non-English13771446Kimi K2.6
LMArena Text: Chinese14181520Kimi K2.6
LMArena Text: German13741451Kimi K2.6
LMArena Text: Japanese13381443Kimi K2.6
LMArena Text: Korean13461427Kimi K2.6
LMArena Text: French14111471Kimi K2.6
LMArena Text: Spanish14211464Kimi K2.6
LMArena Text: Russian13811446Kimi K2.6
LMArena Text: Polish13431438Kimi K2.6
LMArena Text: multi-turn14091453Kimi K2.6
LMArena Text: longer queries14271468Kimi K2.6
LMArena Text: writing and language13861439Kimi K2.6
LMArena Text: entertainment and media13691428Kimi K2.6
LMArena Vision: EnglishNot measured1287Only Kimi K2.6 measured
LMArena Vision: ChineseNot measured1346Only Kimi K2.6 measured
LMArena Vision: reading textNot measured1291Only Kimi K2.6 measured
LMArena Vision: humorNot measured1280Only Kimi K2.6 measured
LMArena Vision: creative writingNot measured1273Only Kimi K2.6 measured
LMArena Document14201451Kimi K2.6
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 Haiku 4.5 and Kimi K2.6
BenchmarkClaude Haiku 4.5Kimi K2.6Leader
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 K2.6$0.0029Fits in one request

Kimi K2.6 costs less

Repository review

50K input + 3K output tokens

Claude Haiku 4.5$0.065Fits in one request
Kimi K2.6$0.059Fits in one request

Kimi K2.6 costs less

Agent loop

200K input + 10K output tokens

Claude Haiku 4.5$0.250Exceeds the context window
Kimi K2.6$0.230Fits in one request

Kimi K2.6 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 K2.6
SpecificationAnthropic Claude Haiku 4.5MoonshotAI Kimi K2.6
MakerAnthropicMoonshot AI
WeightsNo public weights listedOpen weights
ReleasedOctober 15, 2025April 20, 2026
Context window200K262K
Input $/Mtok$1.00$0.95
Output $/Mtok$5.00$4.00
Coding index35.652.1
Independent measurements behind it43
Cost per solved task$0.56$0.35
SourceOpenRouter listingOpenRouter listing

Questions

Is Claude Haiku 4.5 better than Kimi K2.6 for coding?

Pick Kimi K2.6 for coding: it scores 52.1 on the Vibe Coding Index against 35.6 for Claude Haiku 4.5, though on 3 benchmarks against 4. Pick Claude Haiku 4.5 for work measured by MedScribe (Vals AI), where it leads.

Which is cheaper, Claude Haiku 4.5 or Kimi K2.6?

Claude Haiku 4.5 costs $1.00 per million input tokens and $5.00 per million output tokens; Kimi K2.6 costs $0.95 and $4.00. Per solved SWE-bench Verified task, Claude Haiku 4.5 costs $0.56 and Kimi K2.6 $0.35.

Which has the bigger context window, Claude Haiku 4.5 or Kimi K2.6?

Kimi K2.6, with 262K tokens against 200K.

How many benchmarks is the Claude Haiku 4.5 vs Kimi K2.6 comparison based on?

76 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 K2.6's on 3. 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-k2-6" title="Claude Haiku 4.5 vs Kimi K2.6, 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-k2-6">LLMBenchmark.ai, Claude Haiku 4.5 vs Kimi K2.6</a></p>