Enter opens the highlighted result. Esc closes.

Claude Opus 4.5 vs Kimi K2.5

Claude Opus 4.5 leads Kimi K2.5 on coding, 44.0 to 38.6 on the Vibe Coding Index, and Kimi K2.5 costs 8.8x less per output token ($2.85 vs $25.00 per million). Updated October 21, 2026; 78 benchmarks have a result for both.

Replace Claude Opus 4.5 Replace Kimi K2.5
Claude Opus 4.5Anthropic
Coding
44.0
Overall
55.7
Output $/M
$25.00
61
Kimi K2.5Moonshot AI
Coding
38.6
Overall
44.8
Output $/M
$2.85
17
vs boards won of 78 shared

Claude Opus 4.5 or Kimi K2.5: which to pick

Pick Claude Opus 4.5 for coding: it scores 44.0 on the Vibe Coding Index against 38.6 for Kimi K2.5.

Pick Kimi K2.5 for output tokens 8.8x cheaper ($2.85 vs $25.00 per million) and a lower cost per solved task ($0.24 against $1.37).

Model AClaude Opus 4.5Anthropic44.0/1003 independent benchmarks$1.37 per solved taskModel BKimi K2.5Moonshot AI38.6/1003 independent benchmarks$0.24 per solved task
Shared results
78
Claude Opus 4.5 only
30
Kimi K2.5 only
21
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 Opus 4.5 44.0 from 3 benchmarks, Kimi K2.5 38.6 from 3 benchmarks.
Widest category
Coding, 8.3 points apart on average over 13 shared benchmarks.
Widest single gap
ARC-AGI-2: Claude Opus 4.5 37.6% against Kimi K2.5 11.8%, 25.8 points apart on a 0 to 100 scale.
Output price
Claude Opus 4.5 $25.00 against Kimi K2.5 $2.85 per million output tokens, 8.8x apart.
Context window
Claude Opus 4.5 takes 200K tokens, Kimi K2.5 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 Opus 4.5BarsKimi K2.5Ties
Coding121
Intelligence20
Agentic work61
Reasoning83
Math03
Knowledge93
Web design71
General175
All shared boards6117
CodingLike-for-likeSix of these boards feed the Vibe Coding Index121
Coding benchmarks for Claude Opus 4.5 and Kimi K2.5
BenchmarkClaude Opus 4.5Kimi K2.5Leader
SWE-bench Verified79.2%70.8%Claude Opus 4.5
SWE-bench (full test set)52.6%Not measuredOnly Claude Opus 4.5 measured
SWE-bench Multilingual70.7%67.3%Claude Opus 4.5
LMArena WebDev14941437Claude Opus 4.5
AA Coding IndexNot measured46.8Only Kimi K2.5 measured
LiveCodeBench (Vals AI)83.7%83.9%Kimi K2.5
SWE-bench Verified (Vals AI)76.4%70.0%Claude Opus 4.5
Vibe Code Bench (Vals AI)20.6%17.5%Claude Opus 4.5
Code migration (Vals AI)Not measured7.0%Only Kimi K2.5 measured
Terminal-Bench 2.1 (Vals AI)Not measured42.0%Only Kimi K2.5 measured
LiveCodeBench (Artificial Analysis run)87.1%Not measuredOnly Claude Opus 4.5 measured
Terminal-Bench Hard (Artificial Analysis run)47.0%34.8%Claude Opus 4.5
Terminal-Bench63.1%43.2%Claude Opus 4.5
GSO-Bench26.5%Not measuredOnly Claude Opus 4.5 measured
WeirdML63.7%45.6%Claude Opus 4.5
Cybench82.0%Not measuredOnly Claude Opus 4.5 measured
ALE-BenchNot measured821.6Only Kimi K2.5 measured
LMArena Text: coding15031483Claude Opus 4.5
LMArena Text: software and IT14831471Claude Opus 4.5
LMArena WebDev: React14781429Claude Opus 4.5
LMArena WebDev: HTML15101426Claude Opus 4.5
LMArena WebDev: from an imageNot measured1439Only Kimi K2.5 measured
Neither model has a result on the other 17 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
Intelligence benchmarks for Claude Opus 4.5 and Kimi K2.5
BenchmarkClaude Opus 4.5Kimi K2.5Leader
AA Intelligence Index29.123.5Claude Opus 4.5
Epoch Capabilities Index150.1148.1Claude Opus 4.5
Agentic workLike-for-likePublic boards, shown as published, kept out of the index61
Agentic work benchmarks for Claude Opus 4.5 and Kimi K2.5
BenchmarkClaude Opus 4.5Kimi K2.5Leader
Design Arena: agents building web apps11591136Claude Opus 4.5
Design Arena: agents building full-stack apps11561114Claude Opus 4.5
Design Arena: agents building mobile apps11891147Claude Opus 4.5
Design Arena: agents building Android apps11751118Claude Opus 4.5
Design Arena: agents building Godot gamesNot measured1219Only Kimi K2.5 measured
Finance Agent (Vals AI)Not measured35.8%Only Kimi K2.5 measured
Legal Research Bench (Vals AI)Not measured15.9%Only Kimi K2.5 measured
Excel Modeling Benchmark (Vals AI)Not measured28.5%Only Kimi K2.5 measured
τ²-Bench Telecom89.5%95.9%Kimi K2.5
METR time horizons75.0%Not measuredOnly Claude Opus 4.5 measured
Remote Labor Index3.8%Not measuredOnly Claude Opus 4.5 measured
GDPval45.5%Not measuredOnly Claude Opus 4.5 measured
BALROG43.5%Not measuredOnly Claude Opus 4.5 measured
DeepResearch Bench54.8%Not measuredOnly Claude Opus 4.5 measured
OSWorld66.3%63.3%Claude Opus 4.5
Vending-Bench 2$4,967$1,198Claude Opus 4.5
Berkeley Function Calling Leaderboard (BFCL)77.5%Not measuredOnly Claude Opus 4.5 measured
Neither model has a result on the other 24 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index83
Reasoning benchmarks for Claude Opus 4.5 and Kimi K2.5
BenchmarkClaude Opus 4.5Kimi K2.5Leader
GPQA Diamond85.9%84.1%Claude Opus 4.5
MMMU Pro (Vals AI)83.0%84.3%Kimi K2.5
GPQA Diamond (Artificial Analysis run)86.6%87.9%Kimi K2.5
Humanity's Last Exam (Artificial Analysis run)30.1%30.7%Kimi K2.5
GPQA Diamond (Epoch AI run)86.0%Not measuredOnly Claude Opus 4.5 measured
ARC-AGI80.0%65.3%Claude Opus 4.5
ARC-AGI-237.6%11.8%Claude Opus 4.5
SimpleBench62.0%46.8%Claude Opus 4.5
Chess puzzles14.0%Not measuredOnly Claude Opus 4.5 measured
Mystery game puzzles22.0%Not measuredOnly Claude Opus 4.5 measured
EBR-bench14.3%Not measuredOnly Claude Opus 4.5 measured
VPCT40.0%Not measuredOnly Claude Opus 4.5 measured
LMArena Text: hard prompts14761453Claude Opus 4.5
LMArena Text: expert14871466Claude Opus 4.5
LMArena Text: hard prompts in English14821460Claude Opus 4.5
LMArena Vision: diagramsNot measured1282Only Kimi K2.5 measured
LMArena Vision: homeworkNot measured1297Only Kimi K2.5 measured
Kagi LLM Benchmark80.2%78.5%Claude Opus 4.5
Neither model has a result on the other 4 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index03
Math benchmarks for Claude Opus 4.5 and Kimi K2.5
BenchmarkClaude Opus 4.5Kimi K2.5Leader
AIME95.4%95.6%Kimi K2.5
MGSM (Vals AI)95.2%Not measuredOnly Claude Opus 4.5 measured
AA Math Index91.3Not measuredOnly Claude Opus 4.5 measured
AIME 2025 (Artificial Analysis run)91.3%Not measuredOnly Claude Opus 4.5 measured
OTIS Mock AIME86.1%Not measuredOnly Claude Opus 4.5 measured
FrontierMath, tiers 1 to 334.4%Not measuredOnly Claude Opus 4.5 measured
FrontierMath, tier 44.9%Not measuredOnly Claude Opus 4.5 measured
ProofBench36.0%Not measuredOnly Claude Opus 4.5 measured
LMArena Text: math14631470Kimi K2.5
LMArena Text: mathematical work14681473Kimi K2.5
Neither model has a result on the other 3 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index93
Knowledge benchmarks for Claude Opus 4.5 and Kimi K2.5
BenchmarkClaude Opus 4.5Kimi K2.5Leader
MMLU Pro87.3%85.9%Claude Opus 4.5
LegalBench (Vals AI)84.6%Not measuredOnly Claude Opus 4.5 measured
CaseLaw (Vals AI)62.6%58.7%Claude Opus 4.5
CorpFin (Vals AI)65.1%68.3%Kimi K2.5
TaxEval (Vals AI)74.9%74.2%Claude Opus 4.5
MortgageTax (Vals AI)68.7%66.5%Claude Opus 4.5
MedQA (Vals AI)95.9%94.4%Claude Opus 4.5
MedCode (Vals AI)49.2%39.3%Claude Opus 4.5
MMLU Pro (Artificial Analysis run)89.5%Not measuredOnly Claude Opus 4.5 measured
SimpleQA Verified45.7%34.3%Claude Opus 4.5
GeoBench75.0%Not measuredOnly Claude Opus 4.5 measured
LMArena Text: science14541459Kimi K2.5
LMArena Text: medicine and healthcare14441448Kimi K2.5
LMArena Text: legal and government14591441Claude Opus 4.5
LMArena Text: business and finance14481427Claude Opus 4.5
FACTS Benchmark Suite43.9%Not measuredOnly Claude Opus 4.5 measured
Neither model has a result on the other 2 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index71
Web design benchmarks for Claude Opus 4.5 and Kimi K2.5
BenchmarkClaude Opus 4.5Kimi K2.5Leader
Design Arena: websites12471248Kimi K2.5
Design Arena: UI components12381236Claude Opus 4.5
Design Arena: game dev12291207Claude Opus 4.5
Design Arena: data viz12431219Claude Opus 4.5
Design Arena: 3D12141205Claude Opus 4.5
Design Arena: all code categories12421236Claude Opus 4.5
Design Arena: SVG11811149Claude Opus 4.5
Design Arena: ASCII art11901166Claude Opus 4.5
Neither model has a result on the other 1 board here
GeneralLike-for-likePublic boards, shown as published, kept out of the index175
General benchmarks for Claude Opus 4.5 and Kimi K2.5
BenchmarkClaude Opus 4.5Kimi K2.5Leader
SAGE (Vals AI)52.1%49.9%Claude Opus 4.5
MedScribe (Vals AI)85.3%76.4%Claude Opus 4.5
IFBench58.0%70.2%Kimi K2.5
Long context reasoning (AA-LCR)77.3%78.0%Kimi K2.5
DTBench89.9%Not measuredOnly Claude Opus 4.5 measured
LMCA44.5%Not measuredOnly Claude Opus 4.5 measured
Fiction.LiveBenchNot measured86.1%Only Kimi K2.5 measured
CL-bench21.1%19.3%Claude Opus 4.5
Furniture assembly28.3%Not measuredOnly Claude Opus 4.5 measured
CL-bench LifeNot measured13.2%Only Kimi K2.5 measured
LMArena Text14511445Claude Opus 4.5
LMArena Text: instruction following14781431Claude Opus 4.5
LMArena Text: creative writing14451422Claude Opus 4.5
LMArena VisionNot measured1269Only Kimi K2.5 measured
LMArena Text: English14611453Claude Opus 4.5
LMArena Text: non-English14381433Claude Opus 4.5
LMArena Text: Chinese14701494Kimi K2.5
LMArena Text: German14491441Claude Opus 4.5
LMArena Text: Japanese14171423Kimi K2.5
LMArena Text: Korean14241412Claude Opus 4.5
LMArena Text: French14711454Claude Opus 4.5
LMArena Text: Spanish14571450Claude Opus 4.5
LMArena Text: Russian14471435Claude Opus 4.5
LMArena Text: Polish14391445Kimi K2.5
LMArena Text: multi-turn14661444Claude Opus 4.5
LMArena Text: longer queries14791445Claude Opus 4.5
LMArena Text: writing and language14521425Claude Opus 4.5
LMArena Text: entertainment and media14341417Claude Opus 4.5
LMArena Vision: EnglishNot measured1274Only Kimi K2.5 measured
LMArena Vision: ChineseNot measured1328Only Kimi K2.5 measured
LMArena Vision: reading textNot measured1276Only Kimi K2.5 measured
LMArena Vision: humorNot measured1284Only Kimi K2.5 measured
LMArena Vision: captioningNot measured1257Only Kimi K2.5 measured
LMArena Vision: recognizing thingsNot measured1285Only Kimi K2.5 measured
LMArena Vision: creative writingNot measured1269Only Kimi K2.5 measured
LMArena Document1462Not measuredOnly Claude Opus 4.5 measured
Neither model has a result on the other 10 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for Claude Opus 4.5 and Kimi K2.5
BenchmarkClaude Opus 4.5Kimi K2.5Leader
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 Opus 4.5$0.018Fits in one request
Kimi K2.5$0.0020Fits in one request

Kimi K2.5 costs less

Repository review

50K input + 3K output tokens

Claude Opus 4.5$0.325Fits in one request
Kimi K2.5$0.035Fits in one request

Kimi K2.5 costs less

Agent loop

200K input + 10K output tokens

Claude Opus 4.5$1.25Exceeds the context window
Kimi K2.5$0.135Fits in one request

Kimi K2.5 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 Opus 4.5 and Kimi K2.5
SpecificationAnthropic Claude Opus 4.5MoonshotAI Kimi K2.5
MakerAnthropicMoonshot AI
WeightsNo public weights listedOpen weights
ReleasedNovember 24, 2025January 27, 2026
Context window200K262K
Input $/Mtok$5.00$0.532
Output $/Mtok$25.00$2.85
Coding index44.038.6
Independent measurements behind it33
Cost per solved task$1.37$0.24
SourceOpenRouter listingOpenRouter listing

Questions

Is Claude Opus 4.5 better than Kimi K2.5 for coding?

Pick Claude Opus 4.5 for coding: it scores 44.0 on the Vibe Coding Index against 38.6 for Kimi K2.5. Pick Kimi K2.5 for output tokens 8.8x cheaper ($2.85 vs $25.00 per million) and a lower cost per solved task ($0.24 against $1.37).

Which is cheaper, Claude Opus 4.5 or Kimi K2.5?

Claude Opus 4.5 costs $5.00 per million input tokens and $25.00 per million output tokens; Kimi K2.5 costs $0.532 and $2.85. Per solved SWE-bench Verified task, Claude Opus 4.5 costs $1.37 and Kimi K2.5 $0.24.

Which has the bigger context window, Claude Opus 4.5 or Kimi K2.5?

Kimi K2.5, with 262K tokens against 200K.

How many benchmarks is the Claude Opus 4.5 vs Kimi K2.5 comparison based on?

78 benchmarks have a result for both models as of October 21, 2026. Claude Opus 4.5's coding index rests on 3 independent benchmarks and Kimi K2.5'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-opus-4-5-vs-kimi-k2-5" title="Claude Opus 4.5 vs Kimi K2.5, 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-opus-4-5-vs-kimi-k2-5">LLMBenchmark.ai, Claude Opus 4.5 vs Kimi K2.5</a></p>