Enter opens the highlighted result. Esc closes.

Claude Opus 4.6 vs Kimi K2.5

Claude Opus 4.6 leads Kimi K2.5 on coding, 57.2 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 22, 2026; 88 benchmarks have a result for both.

Replace Claude Opus 4.6 Replace Kimi K2.5
Claude Opus 4.6Anthropic
Coding
57.2
Overall
66.0
Output $/M
$25.00
81
Kimi K2.5Moonshot AI
Coding
38.6
Overall
44.8
Output $/M
$2.85
5
vs boards won of 88 shared, 2 tied

Claude Opus 4.6 or Kimi K2.5: which to pick

Pick Claude Opus 4.6 for coding: it scores 57.2 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 $1.56).

Model AClaude Opus 4.6Anthropic57.2/1004 independent benchmarks$1.56 per solved taskModel BKimi K2.5Moonshot AI38.6/1003 independent benchmarks$0.24 per solved task
Shared results
88
Claude Opus 4.6 only
22
Kimi K2.5 only
11
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 4.6 57.2 from 4 benchmarks, Kimi K2.5 38.6 from 3 benchmarks.
Widest category
Coding, 16.6 points apart on average over 14 shared benchmarks.
Widest single gap
ARC-AGI-2: Claude Opus 4.6 69.2% against Kimi K2.5 11.8%, 57.4 points apart on a 0 to 100 scale.
Output price
Claude Opus 4.6 $25.00 against Kimi K2.5 $2.85 per million output tokens, 8.8x apart.
Context window
Claude Opus 4.6 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 4.6BarsKimi K2.5Ties
Coding140
Intelligence20
Agentic work51
Reasoning121
Math201 tie
Knowledge111
Web design80
General2721 tie
All shared boards8152 ties
CodingLike-for-likeSix of these boards feed the Vibe Coding Index140
Coding benchmarks for Claude Opus 4.6 and Kimi K2.5
BenchmarkClaude Opus 4.6Kimi K2.5Leader
SWE-bench Verified75.6%70.8%Claude Opus 4.6
SWE-bench Multilingual72.0%67.3%Claude Opus 4.6
LMArena WebDev15471437Claude Opus 4.6
AA Coding IndexNot measured46.8Only Kimi K2.5 measured
LiveCodeBench (Vals AI)84.7%83.9%Claude Opus 4.6
SWE-bench Verified (Vals AI)78.2%70.0%Claude Opus 4.6
Vibe Code Bench (Vals AI)57.6%17.5%Claude Opus 4.6
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
Terminal-Bench Hard (Artificial Analysis run)48.5%34.8%Claude Opus 4.6
Terminal-Bench79.8%43.2%Claude Opus 4.6
FrontierCode26.6%Not measuredOnly Claude Opus 4.6 measured
GSO-Bench41.2%Not measuredOnly Claude Opus 4.6 measured
WeirdML78.0%45.6%Claude Opus 4.6
Cybench93.0%Not measuredOnly Claude Opus 4.6 measured
ALE-BenchNot measured821.6Only Kimi K2.5 measured
LMArena Text: coding15341483Claude Opus 4.6
LMArena Text: software and IT15271471Claude Opus 4.6
LMArena WebDev: React15391429Claude Opus 4.6
LMArena WebDev: HTML15591426Claude Opus 4.6
LMArena WebDev: from an image15431439Claude Opus 4.6
Neither model has a result on the other 18 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
Intelligence benchmarks for Claude Opus 4.6 and Kimi K2.5
BenchmarkClaude Opus 4.6Kimi K2.5Leader
AA Intelligence Index31.923.5Claude Opus 4.6
Epoch Capabilities Index155.7148.1Claude Opus 4.6
Agentic workLike-for-likePublic boards, shown as published, kept out of the index51
Agentic work benchmarks for Claude Opus 4.6 and Kimi K2.5
BenchmarkClaude Opus 4.6Kimi K2.5Leader
Design Arena: agents building web apps12061136Claude Opus 4.6
Design Arena: agents building full-stack apps12201114Claude Opus 4.6
Design Arena: agents building mobile apps12071147Claude Opus 4.6
Design Arena: agents building Android apps11971118Claude Opus 4.6
Design Arena: agents building Godot gamesNot measured1219Only Kimi K2.5 measured
Design Arena: agents building games1212Not measuredOnly Claude Opus 4.6 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 Telecom92.1%95.9%Kimi K2.5
APEX-Agents46.3%Not measuredOnly Claude Opus 4.6 measured
METR time horizons78.9%Not measuredOnly Claude Opus 4.6 measured
Remote Labor Index4.2%Not measuredOnly Claude Opus 4.6 measured
DeepResearch Bench55.3%Not measuredOnly Claude Opus 4.6 measured
OSWorldNot measured63.3%Only Kimi K2.5 measured
Vending-Bench 2$8,018$1,198Claude Opus 4.6
Neither model has a result on the other 25 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index121
Reasoning benchmarks for Claude Opus 4.6 and Kimi K2.5
BenchmarkClaude Opus 4.6Kimi K2.5Leader
GPQA Diamond89.7%84.1%Claude Opus 4.6
MMMU Pro (Vals AI)83.9%84.3%Kimi K2.5
GPQA Diamond (Artificial Analysis run)89.6%87.9%Claude Opus 4.6
Humanity's Last Exam (Artificial Analysis run)39.9%30.7%Claude Opus 4.6
GPQA Diamond (Epoch AI run)90.5%Not measuredOnly Claude Opus 4.6 measured
ARC-AGI94.0%65.3%Claude Opus 4.6
ARC-AGI-269.2%11.8%Claude Opus 4.6
SimpleBench67.6%46.8%Claude Opus 4.6
Chess puzzles21.0%Not measuredOnly Claude Opus 4.6 measured
Mystery game puzzles25.0%Not measuredOnly Claude Opus 4.6 measured
EBR-bench12.7%Not measuredOnly Claude Opus 4.6 measured
LMArena Text: hard prompts15251453Claude Opus 4.6
LMArena Text: expert15441466Claude Opus 4.6
LMArena Text: hard prompts in English15301460Claude Opus 4.6
LMArena Vision: diagrams13401282Claude Opus 4.6
LMArena Vision: homework13371297Claude Opus 4.6
Kagi LLM Benchmark83.6%78.5%Claude Opus 4.6
Neither model has a result on the other 5 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index20
Math benchmarks for Claude Opus 4.6 and Kimi K2.5
BenchmarkClaude Opus 4.6Kimi K2.5Leader
AIME95.6%95.6%Tie
OTIS Mock AIME94.4%Not measuredOnly Claude Opus 4.6 measured
FrontierMath, tiers 1 to 366.0%Not measuredOnly Claude Opus 4.6 measured
FrontierMath, tier 426.8%Not measuredOnly Claude Opus 4.6 measured
ProofBench50.0%Not measuredOnly Claude Opus 4.6 measured
LMArena Text: math15181470Claude Opus 4.6
LMArena Text: mathematical work15251473Claude Opus 4.6
Neither model has a result on the other 6 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index111
Knowledge benchmarks for Claude Opus 4.6 and Kimi K2.5
BenchmarkClaude Opus 4.6Kimi K2.5Leader
MMLU Pro89.1%85.9%Claude Opus 4.6
LegalBench (Vals AI)85.3%Not measuredOnly Claude Opus 4.6 measured
CaseLaw (Vals AI)62.1%58.7%Claude Opus 4.6
CorpFin (Vals AI)67.0%68.3%Kimi K2.5
TaxEval (Vals AI)76.0%74.2%Claude Opus 4.6
MortgageTax (Vals AI)68.5%66.5%Claude Opus 4.6
MedQA (Vals AI)95.4%94.4%Claude Opus 4.6
MedCode (Vals AI)49.1%39.3%Claude Opus 4.6
SimpleQA Verified47.0%34.3%Claude Opus 4.6
LMArena Text: science15191459Claude Opus 4.6
LMArena Text: medicine and healthcare15041448Claude Opus 4.6
LMArena Text: legal and government15121441Claude Opus 4.6
LMArena Text: business and finance14971427Claude Opus 4.6
FACTS Benchmark Suite41.5%Not measuredOnly Claude Opus 4.6 measured
Neither model has a result on the other 4 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index80
Web design benchmarks for Claude Opus 4.6 and Kimi K2.5
BenchmarkClaude Opus 4.6Kimi K2.5Leader
Design Arena: websites12911248Claude Opus 4.6
Design Arena: UI components12811234Claude Opus 4.6
Design Arena: game dev12771206Claude Opus 4.6
Design Arena: data viz12791219Claude Opus 4.6
Design Arena: 3D12731204Claude Opus 4.6
Design Arena: all code categories12881236Claude Opus 4.6
Design Arena: SVG12271149Claude Opus 4.6
Design Arena: ASCII art12551166Claude Opus 4.6
Neither model has a result on the other 1 board here
GeneralLike-for-likePublic boards, shown as published, kept out of the index272
General benchmarks for Claude Opus 4.6 and Kimi K2.5
BenchmarkClaude Opus 4.6Kimi K2.5Leader
SAGE (Vals AI)51.6%49.9%Claude Opus 4.6
MedScribe (Vals AI)86.7%76.4%Claude Opus 4.6
IFBench53.1%70.2%Kimi K2.5
Long context reasoning (AA-LCR)78.0%78.0%Tie
DTBench91.2%Not measuredOnly Claude Opus 4.6 measured
LMCA55.8%Not measuredOnly Claude Opus 4.6 measured
Fiction.LiveBenchNot measured86.1%Only Kimi K2.5 measured
CL-bench20.7%19.3%Claude Opus 4.6
Furniture assembly28.3%Not measuredOnly Claude Opus 4.6 measured
CL-bench Life17.0%13.2%Claude Opus 4.6
LMArena Text15011445Claude Opus 4.6
LMArena Text: instruction following15211431Claude Opus 4.6
LMArena Text: creative writing15051422Claude Opus 4.6
LMArena Vision13161269Claude Opus 4.6
LMArena Text: English15111453Claude Opus 4.6
LMArena Text: non-English14881433Claude Opus 4.6
LMArena Text: Chinese15511494Claude Opus 4.6
LMArena Text: German15001441Claude Opus 4.6
LMArena Text: Japanese14881423Claude Opus 4.6
LMArena Text: Korean14641412Claude Opus 4.6
LMArena Text: French15121454Claude Opus 4.6
LMArena Text: Spanish15101450Claude Opus 4.6
LMArena Text: Russian14971435Claude Opus 4.6
LMArena Text: Polish14991445Claude Opus 4.6
LMArena Text: multi-turn15111444Claude Opus 4.6
LMArena Text: longer queries15181445Claude Opus 4.6
LMArena Text: writing and language15021425Claude Opus 4.6
LMArena Text: entertainment and media14921417Claude Opus 4.6
LMArena Vision: English13241274Claude Opus 4.6
LMArena Vision: Chinese13701328Claude Opus 4.6
LMArena Vision: reading text13261276Claude Opus 4.6
LMArena Vision: humor13141284Claude Opus 4.6
LMArena Vision: captioningNot measured1257Only Kimi K2.5 measured
LMArena Vision: recognizing things12741285Kimi K2.5
LMArena Vision: creative writing13311269Claude Opus 4.6
LMArena Document1507Not measuredOnly Claude Opus 4.6 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 4.6 and Kimi K2.5
BenchmarkClaude Opus 4.6Kimi 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 4.6$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 4.6$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 4.6$1.25Fits 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 4.6 and Kimi K2.5
SpecificationAnthropic Claude Opus 4.6MoonshotAI Kimi K2.5
MakerAnthropicMoonshot AI
WeightsNo public weights listedOpen weights
ReleasedFebruary 4, 2026January 27, 2026
Context window1M262K
Input $/Mtok$5.00$0.532
Output $/Mtok$25.00$2.85
Coding index57.238.6
Independent measurements behind it43
Cost per solved task$1.56$0.24
SourceOpenRouter listingOpenRouter listing

Questions

Is Claude Opus 4.6 better than Kimi K2.5 for coding?

Pick Claude Opus 4.6 for coding: it scores 57.2 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 $1.56).

Which is cheaper, Claude Opus 4.6 or Kimi K2.5?

Claude Opus 4.6 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 4.6 costs $1.56 and Kimi K2.5 $0.24.

Which has the bigger context window, Claude Opus 4.6 or Kimi K2.5?

Claude Opus 4.6, with 1M tokens against 262K.

How many benchmarks is the Claude Opus 4.6 vs Kimi K2.5 comparison based on?

88 benchmarks have a result for both models as of October 22, 2026. Claude Opus 4.6's coding index rests on 4 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-4-6-vs-kimi-k2-5" title="Claude Opus 4.6 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-4-6-vs-kimi-k2-5">LLMBenchmark.ai, Claude Opus 4.6 vs Kimi K2.5</a></p>