Enter opens the highlighted result. Esc closes.

Claude Opus 5.5 vs Kimi K2.5

Claude Opus 5.5 leads Kimi K2.5 on coding, 88.8 to 38.6 on the Vibe Coding Index, and Kimi K2.5 costs 7.0x less per output token ($2.85 vs $20.00 per million). Updated October 22, 2026; 62 benchmarks have a result for both.

Replace Claude Opus 5.5 Replace Kimi K2.5
Claude Opus 5.5Anthropic
Coding
88.8
Overall
87.1
Output $/M
$20.00
61
Kimi K2.5Moonshot AI
Coding
38.6
Overall
44.8
Output $/M
$2.85
1
vs boards won of 62 shared

Claude Opus 5.5 or Kimi K2.5: which to pick

Pick Claude Opus 5.5 for coding: it scores 88.8 on the Vibe Coding Index against 38.6 for Kimi K2.5.

Pick Kimi K2.5 for output tokens 7.0x cheaper ($2.85 vs $20.00 per million) and work measured by SAGE (Vals AI), where it leads.

Model AClaude Opus 5.5Anthropic88.8/1005 independent benchmarksNo cost per solved taskModel BKimi K2.5Moonshot AI38.6/1003 independent benchmarks$0.24 per solved task
Shared results
62
Claude Opus 5.5 only
47
Kimi K2.5 only
37
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 5.5 88.8 from 5 benchmarks, Kimi K2.5 38.6 from 3 benchmarks.
Widest category
Coding, 38.1 points apart on average over 10 shared benchmarks.
Widest single gap
ARC-AGI-2: Claude Opus 5.5 93.3% against Kimi K2.5 11.8%, 81.5 points apart on a 0 to 100 scale.
Output price
Claude Opus 5.5 $20.00 against Kimi K2.5 $2.85 per million output tokens, 7.0x apart.
Context window
Claude Opus 5.5 takes 1M 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 5.5BarsKimi K2.5Ties
Coding100
Intelligence20
Agentic work60
Reasoning80
Math20
Knowledge60
Web design70
General201
All shared boards611
CodingLike-for-likeSix of these boards feed the Vibe Coding Index100
Coding benchmarks for Claude Opus 5.5 and Kimi K2.5
BenchmarkClaude Opus 5.5Kimi K2.5Leader
SWE-bench VerifiedNot measured70.8%Only Kimi K2.5 measured
SWE-bench MultilingualNot measured67.3%Only Kimi K2.5 measured
LiveBench coding96.3%Not measuredOnly Claude Opus 5.5 measured
LMArena WebDev18071437Claude Opus 5.5
AA Coding IndexNot measured46.8Only Kimi K2.5 measured
LiveCodeBench (Vals AI)Not measured83.9%Only Kimi K2.5 measured
SWE-bench Verified (Vals AI)Not measured70.0%Only Kimi K2.5 measured
Terminal-Bench 4 (Vals AI)65.2%Not measuredOnly Claude Opus 5.5 measured
Vibe Code Bench (Vals AI)90.3%17.5%Claude Opus 5.5
Code migration (Vals AI)66.7%7.0%Claude Opus 5.5
ProgramBench (Vals AI)18.5%Not measuredOnly Claude Opus 5.5 measured
IOI (Vals AI)95.1%Not measuredOnly Claude Opus 5.5 measured
Terminal-Bench 2.1 (Vals AI)87.6%42.0%Claude Opus 5.5
SWE-bench Multimodal (Vals AI)70.2%Not measuredOnly Claude Opus 5.5 measured
Vibe Code Bench 1-100 (Vals AI)30.4%Not measuredOnly Claude Opus 5.5 measured
CyberBench (Vals AI)74.6%Not measuredOnly Claude Opus 5.5 measured
SciCode66.9%Not measuredOnly Claude Opus 5.5 measured
Terminal-Bench Hard (Artificial Analysis run)Not measured34.8%Only Kimi K2.5 measured
Terminal-BenchNot measured43.2%Only Kimi K2.5 measured
FrontierCode54.6%Not measuredOnly Claude Opus 5.5 measured
FrontierSWE62.3%Not measuredOnly Claude Opus 5.5 measured
WeirdMLNot measured45.6%Only Kimi K2.5 measured
MirrorCode77.4%Not measuredOnly Claude Opus 5.5 measured
ALE-Bench2147.4821.6Claude Opus 5.5
LMArena Text: coding15451483Claude Opus 5.5
LMArena Text: software and IT15381471Claude Opus 5.5
LMArena WebDev: React18551429Claude Opus 5.5
LMArena WebDev: HTML17531426Claude Opus 5.5
LMArena WebDev: from an image17531439Claude Opus 5.5
SciCode18.5%Not measuredOnly Claude Opus 5.5 measured
Neither model has a result on the other 9 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
Intelligence benchmarks for Claude Opus 5.5 and Kimi K2.5
BenchmarkClaude Opus 5.5Kimi K2.5Leader
AA Intelligence Index57.623.5Claude Opus 5.5
Epoch Capabilities Index168.8148.1Claude Opus 5.5
Agentic workLike-for-likePublic boards, shown as published, kept out of the index60
Agentic work benchmarks for Claude Opus 5.5 and Kimi K2.5
BenchmarkClaude Opus 5.5Kimi K2.5Leader
Design Arena: agents building web apps13161136Claude Opus 5.5
Design Arena: agents building full-stack appsNot measured1114Only Kimi K2.5 measured
Design Arena: agents building mobile apps13081147Claude Opus 5.5
Design Arena: agents building Android appsNot measured1118Only Kimi K2.5 measured
Design Arena: agents building Godot gamesNot measured1219Only Kimi K2.5 measured
Design Arena: spreadsheets1368Not measuredOnly Claude Opus 5.5 measured
LiveBench research85.0%Not measuredOnly Claude Opus 5.5 measured
LiveBench browser80.0%Not measuredOnly Claude Opus 5.5 measured
LiveBench long agentic85.0%Not measuredOnly Claude Opus 5.5 measured
SREBench (Vals AI)33.6%Not measuredOnly Claude Opus 5.5 measured
Finance Agent (Vals AI)58.6%35.8%Claude Opus 5.5
Tax Agent Bench (Vals AI)45.6%Not measuredOnly Claude Opus 5.5 measured
Legal Research Bench (Vals AI)50.5%15.9%Claude Opus 5.5
Harvey's Legal Agent Benchmark (Vals AI)9.2%Not measuredOnly Claude Opus 5.5 measured
Excel Modeling Benchmark (Vals AI)75.9%28.5%Claude Opus 5.5
BioMysteryBench (Vals AI)79.3%Not measuredOnly Claude Opus 5.5 measured
Terminal-Bench-Science (Vals AI)47.1%Not measuredOnly Claude Opus 5.5 measured
Vals Science Index58.7%Not measuredOnly Claude Opus 5.5 measured
Time Horizon Index (Vals AI)91.3%Not measuredOnly Claude Opus 5.5 measured
CUA-bench (Vals AI)14.0%Not measuredOnly Claude Opus 5.5 measured
Robo-bench (Vals AI)14.6%Not measuredOnly Claude Opus 5.5 measured
τ²-Bench TelecomNot measured95.9%Only Kimi K2.5 measured
APEX-Agents73.5%Not measuredOnly Claude Opus 5.5 measured
Remote Labor Index21.3%Not measuredOnly Claude Opus 5.5 measured
OSWorldNot measured63.3%Only Kimi K2.5 measured
SpireClimb3.3%Not measuredOnly Claude Opus 5.5 measured
Vending-Bench 2$9,235$1,198Claude Opus 5.5
LMArena Search1213Not measuredOnly Claude Opus 5.5 measured
Neither model has a result on the other 13 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index80
Reasoning benchmarks for Claude Opus 5.5 and Kimi K2.5
BenchmarkClaude Opus 5.5Kimi K2.5Leader
GPQA DiamondNot measured84.1%Only Kimi K2.5 measured
LiveBench reasoning92.2%Not measuredOnly Claude Opus 5.5 measured
MysteryMechanism (Vals AI)49.5%Not measuredOnly Claude Opus 5.5 measured
MMMU Pro (Vals AI)Not measured84.3%Only Kimi K2.5 measured
GPQA Diamond (Artificial Analysis run)Not measured87.9%Only Kimi K2.5 measured
Humanity's Last Exam (Artificial Analysis run)61.4%30.7%Claude Opus 5.5
GPQA Diamond (Epoch AI run)90.6%Not measuredOnly Claude Opus 5.5 measured
ARC-AGI98.5%65.3%Claude Opus 5.5
ARC-AGI-293.3%11.8%Claude Opus 5.5
SimpleBenchNot measured46.8%Only Kimi K2.5 measured
Chess puzzles67.0%Not measuredOnly Claude Opus 5.5 measured
Mystery game puzzles71.0%Not measuredOnly Claude Opus 5.5 measured
EBR-bench71.4%Not measuredOnly Claude Opus 5.5 measured
LMArena Text: hard prompts15361453Claude Opus 5.5
LMArena Text: expert15491466Claude Opus 5.5
LMArena Text: hard prompts in English15351460Claude Opus 5.5
LMArena Vision: diagrams13451282Claude Opus 5.5
LMArena Vision: homework13621297Claude Opus 5.5
Kagi LLM BenchmarkNot measured78.5%Only Kimi K2.5 measured
Neither model has a result on the other 3 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index20
Math benchmarks for Claude Opus 5.5 and Kimi K2.5
BenchmarkClaude Opus 5.5Kimi K2.5Leader
AIMENot measured95.6%Only Kimi K2.5 measured
OTIS Mock AIME100.0%Not measuredOnly Claude Opus 5.5 measured
FrontierMath, tiers 1 to 391.2%Not measuredOnly Claude Opus 5.5 measured
FrontierMath, tier 495.0%Not measuredOnly Claude Opus 5.5 measured
ProofBench100.0%Not measuredOnly Claude Opus 5.5 measured
LMArena Text: math15181470Claude Opus 5.5
LMArena Text: mathematical work15161473Claude Opus 5.5
Neither model has a result on the other 6 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index60
Knowledge benchmarks for Claude Opus 5.5 and Kimi K2.5
BenchmarkClaude Opus 5.5Kimi K2.5Leader
MMLU ProNot measured85.9%Only Kimi K2.5 measured
CaseLaw (Vals AI)Not measured58.7%Only Kimi K2.5 measured
CorpFin (Vals AI)Not measured68.3%Only Kimi K2.5 measured
TaxEval (Vals AI)Not measured74.2%Only Kimi K2.5 measured
MortgageTax (Vals AI)Not measured66.5%Only Kimi K2.5 measured
MedQA (Vals AI)Not measured94.4%Only Kimi K2.5 measured
MedCode (Vals AI)49.8%39.3%Claude Opus 5.5
SimpleQA Verified72.2%34.3%Claude Opus 5.5
LMArena Text: science15241459Claude Opus 5.5
LMArena Text: medicine and healthcare15091448Claude Opus 5.5
LMArena Text: legal and government15181441Claude Opus 5.5
LMArena Text: business and finance14941427Claude Opus 5.5
FACTS Benchmark Suite65.3%Not measuredOnly Claude Opus 5.5 measured
Neither model has a result on the other 5 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index70
Web design benchmarks for Claude Opus 5.5 and Kimi K2.5
BenchmarkClaude Opus 5.5Kimi K2.5Leader
Design Arena: websites13351248Claude Opus 5.5
Design Arena: UI components13851234Claude Opus 5.5
Design Arena: game dev14611206Claude Opus 5.5
Design Arena: data viz13971219Claude Opus 5.5
Design Arena: 3D14761204Claude Opus 5.5
Design Arena: all code categories13901236Claude Opus 5.5
Design Arena: SVG13291149Claude Opus 5.5
Design Arena: ASCII artNot measured1166Only Kimi K2.5 measured
LiveBench design86.9%Not measuredOnly Claude Opus 5.5 measured
GeneralLike-for-likePublic boards, shown as published, kept out of the index201
General benchmarks for Claude Opus 5.5 and Kimi K2.5
BenchmarkClaude Opus 5.5Kimi K2.5Leader
Vals Index70.2%Not measuredOnly Claude Opus 5.5 measured
LiveBench data analysis80.3%Not measuredOnly Claude Opus 5.5 measured
Public Benefits Bench (Vals AI)70.6%Not measuredOnly Claude Opus 5.5 measured
SAGE (Vals AI)45.8%49.9%Kimi K2.5
MedScribe (Vals AI)91.4%76.4%Claude Opus 5.5
IFBenchNot measured70.2%Only Kimi K2.5 measured
Long context reasoning (AA-LCR)84.7%78.0%Claude Opus 5.5
DTBench98.9%Not measuredOnly Claude Opus 5.5 measured
LMCA68.2%Not measuredOnly Claude Opus 5.5 measured
Fiction.LiveBenchNot measured86.1%Only Kimi K2.5 measured
CL-benchNot measured19.3%Only Kimi K2.5 measured
Furniture assembly83.3%Not measuredOnly Claude Opus 5.5 measured
CL-bench LifeNot measured13.2%Only Kimi K2.5 measured
LMArena Text15161445Claude Opus 5.5
LMArena Text: instruction following15371431Claude Opus 5.5
LMArena Text: creative writing15351422Claude Opus 5.5
LMArena Vision13211269Claude Opus 5.5
LMArena Text: English15191453Claude Opus 5.5
LMArena Text: non-English15071433Claude Opus 5.5
LMArena Text: Chinese15821494Claude Opus 5.5
LMArena Text: GermanNot measured1441Only Kimi K2.5 measured
LMArena Text: Japanese15341423Claude Opus 5.5
LMArena Text: KoreanNot measured1412Only Kimi K2.5 measured
LMArena Text: French14931454Claude Opus 5.5
LMArena Text: Spanish15081450Claude Opus 5.5
LMArena Text: Russian15171435Claude Opus 5.5
LMArena Text: PolishNot measured1445Only Kimi K2.5 measured
LMArena Text: multi-turn15011444Claude Opus 5.5
LMArena Text: longer queries15321445Claude Opus 5.5
LMArena Text: writing and language15321425Claude Opus 5.5
LMArena Text: entertainment and media15151417Claude Opus 5.5
LMArena Vision: English13171274Claude Opus 5.5
LMArena Vision: ChineseNot measured1328Only Kimi K2.5 measured
LMArena Vision: reading text13261276Claude Opus 5.5
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 writing13201269Claude Opus 5.5
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 Opus 5.5 and Kimi K2.5
BenchmarkClaude Opus 5.5Kimi 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 5.5$0.014Fits 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 5.5$0.260Fits 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 5.5$1.00Fits in one request
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 5.5 and Kimi K2.5
SpecificationAnthropic Claude Opus 5.5MoonshotAI Kimi K2.5
MakerAnthropicMoonshot AI
WeightsNo public weights listedOpen weights
ReleasedSeptember 22, 2026January 27, 2026
Context window1M262K
Input $/Mtok$4.00$0.532
Output $/Mtok$20.00$2.85
Coding index88.838.6
Independent measurements behind it53
Cost per solved taskNot computable$0.24
SourceOpenRouter listingOpenRouter listing

Questions

Is Claude Opus 5.5 better than Kimi K2.5 for coding?

Pick Claude Opus 5.5 for coding: it scores 88.8 on the Vibe Coding Index against 38.6 for Kimi K2.5. Pick Kimi K2.5 for output tokens 7.0x cheaper ($2.85 vs $20.00 per million) and work measured by SAGE (Vals AI), where it leads.

Which is cheaper, Claude Opus 5.5 or Kimi K2.5?

Claude Opus 5.5 costs $4.00 per million input tokens and $20.00 per million output tokens; Kimi K2.5 costs $0.532 and $2.85. Cost per solved task is known for Kimi K2.5 only.

Which has the bigger context window, Claude Opus 5.5 or Kimi K2.5?

Claude Opus 5.5, with 1M tokens against 262K.

How many benchmarks is the Claude Opus 5.5 vs Kimi K2.5 comparison based on?

62 benchmarks have a result for both models as of October 22, 2026. Claude Opus 5.5's coding index rests on 5 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-5-5-vs-kimi-k2-5" title="Claude Opus 5.5 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-5-5-vs-kimi-k2-5">LLMBenchmark.ai, Claude Opus 5.5 vs Kimi K2.5</a></p>