Enter opens the highlighted result. Esc closes.

Claude Opus 4.8 vs Kimi K2.6

Claude Opus 4.8 leads Kimi K2.6 on coding, 65.0 to 52.1 on the Vibe Coding Index, and Kimi K2.6 costs 6.3x less per output token ($4.00 vs $25.00 per million). Updated October 22, 2026; 105 benchmarks have a result for both.

Replace Claude Opus 4.8 Replace Kimi K2.6
Claude Opus 4.8Anthropic
Coding
65.0
Overall
69.8
Output $/M
$25.00
90
Kimi K2.6Moonshot AI
Coding
52.1
Overall
60.5
Output $/M
$4.00
15
vs boards won of 105 shared

Claude Opus 4.8 or Kimi K2.6: which to pick

Pick Claude Opus 4.8 for coding: it scores 65.0 on the Vibe Coding Index against 52.1 for Kimi K2.6.

Pick Kimi K2.6 for output tokens 6.3x cheaper ($4.00 vs $25.00 per million) and a lower cost per solved task ($0.35 against $2.17).

Model AClaude Opus 4.8Anthropic65.0/1006 independent benchmarks$2.17 per solved taskModel BKimi K2.6Moonshot AI52.1/1003 independent benchmarks$0.35 per solved task
Shared results
105
Claude Opus 4.8 only
25
Kimi K2.6 only
4
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 4.8 65.0 from 6 benchmarks, Kimi K2.6 52.1 from 3 benchmarks.
Widest category
Math, 18.9 points apart on average over 6 shared benchmarks.
Widest single gap
ProofBench: Claude Opus 4.8 69.0% against Kimi K2.6 16.0%, 53.0 points apart on a 0 to 100 scale.
Output price
Claude Opus 4.8 $25.00 against Kimi K2.6 $4.00 per million output tokens, 6.3x apart.
Context window
Claude Opus 4.8 takes 1M 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 Opus 4.8BarsKimi K2.6Ties
Coding150
Intelligence20
Agentic work143
Reasoning130
Math60
Knowledge92
Web design35
General285
All shared boards9015
CodingLike-for-likeSix of these boards feed the Vibe Coding Index150
Coding benchmarks for Claude Opus 4.8 and Kimi K2.6
BenchmarkClaude Opus 4.8Kimi K2.6Leader
LiveBench coding77.3%Not measuredOnly Claude Opus 4.8 measured
LMArena WebDev15561509Claude Opus 4.8
AA Coding Index74.361.8Claude Opus 4.8
LiveCodeBench (Vals AI)87.8%86.8%Claude Opus 4.8
SWE-bench Verified (Vals AI)88.6%76.2%Claude Opus 4.8
Terminal-Bench 4 (Vals AI)23.2%Not measuredOnly Claude Opus 4.8 measured
Vibe Code Bench (Vals AI)82.7%37.9%Claude Opus 4.8
Code migration (Vals AI)47.3%27.8%Claude Opus 4.8
ProgramBench (Vals AI)1.0%0.0%Claude Opus 4.8
Terminal-Bench 2.1 (Vals AI)71.9%53.6%Claude Opus 4.8
SkillsBench (Vals AI)59.2%Not measuredOnly Claude Opus 4.8 measured
SciCode54.4%51.5%Claude Opus 4.8
Terminal-Bench Hard (Artificial Analysis run)58.3%43.9%Claude Opus 4.8
FrontierCode46.5%Not measuredOnly Claude Opus 4.8 measured
GSO-Bench47.1%Not measuredOnly Claude Opus 4.8 measured
WeirdML82.9%55.9%Claude Opus 4.8
ALE-BenchNot measured1092.7Only Kimi K2.6 measured
LMArena Text: coding14901489Claude Opus 4.8
LMArena Text: software and IT14881484Claude Opus 4.8
LMArena WebDev: React15571505Claude Opus 4.8
LMArena WebDev: HTML15431485Claude Opus 4.8
LMArena WebDev: from an imageNot measured1521Only Kimi K2.6 measured
SciCode12.3%Not measuredOnly Claude Opus 4.8 measured
Neither model has a result on the other 16 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
Intelligence benchmarks for Claude Opus 4.8 and Kimi K2.6
BenchmarkClaude Opus 4.8Kimi K2.6Leader
AA Intelligence Index41.827.0Claude Opus 4.8
Epoch Capabilities Index159.0150.9Claude Opus 4.8
Agentic workLike-for-likePublic boards, shown as published, kept out of the index143
Agentic work benchmarks for Claude Opus 4.8 and Kimi K2.6
BenchmarkClaude Opus 4.8Kimi K2.6Leader
AA Agentic Index41.920.5Claude Opus 4.8
Design Arena: agents building web apps12331268Kimi K2.6
Design Arena: agents building full-stack apps12491155Claude Opus 4.8
Design Arena: agents building mobile apps12221156Claude Opus 4.8
Design Arena: agents building Android apps12331161Claude Opus 4.8
Design Arena: agents building Godot games12311120Claude Opus 4.8
Design Arena: agents building games12391141Claude Opus 4.8
Design Arena: HTML slides11711135Claude Opus 4.8
Design Arena: PowerPoint slides12021103Claude Opus 4.8
Design Arena: spreadsheets13031276Claude Opus 4.8
LiveBench research81.8%Not measuredOnly Claude Opus 4.8 measured
LiveBench browser96.0%Not measuredOnly Claude Opus 4.8 measured
LiveBench long agentic48.3%Not measuredOnly Claude Opus 4.8 measured
Finance Agent (Vals AI)53.9%44.9%Claude Opus 4.8
Tax Agent Bench (Vals AI)30.0%12.4%Claude Opus 4.8
Legal Research Bench (Vals AI)43.8%15.9%Claude Opus 4.8
Excel Modeling Benchmark (Vals AI)69.4%57.9%Claude Opus 4.8
Terminal-Bench-Science (Vals AI)4.3%Not measuredOnly Claude Opus 4.8 measured
Time Horizon Index (Vals AI)11.8%Not measuredOnly Claude Opus 4.8 measured
τ²-Bench Telecom94.4%95.9%Kimi K2.6
APEX-Agents48.9%Not measuredOnly Claude Opus 4.8 measured
Remote Labor Index8.3%Not measuredOnly Claude Opus 4.8 measured
OSWorld 2.020.6%4.6%Claude Opus 4.8
DeepResearch Bench50.2%Not measuredOnly Claude Opus 4.8 measured
PostTrainBench33.8%Not measuredOnly Claude Opus 4.8 measured
Vending-Bench 2$5,787$6,205Kimi K2.6
LMArena Search1204Not measuredOnly Claude Opus 4.8 measured
Neither model has a result on the other 14 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index130
Reasoning benchmarks for Claude Opus 4.8 and Kimi K2.6
BenchmarkClaude Opus 4.8Kimi K2.6Leader
GPQA Diamond92.4%89.1%Claude Opus 4.8
LiveBench reasoning89.2%Not measuredOnly Claude Opus 4.8 measured
MMMU Pro (Vals AI)86.6%86.3%Claude Opus 4.8
GPQA Diamond (Artificial Analysis run)92.0%91.1%Claude Opus 4.8
Humanity's Last Exam (Artificial Analysis run)48.7%37.5%Claude Opus 4.8
GPQA Diamond (Epoch AI run)91.0%90.8%Claude Opus 4.8
ARC-AGI92.5%Not measuredOnly Claude Opus 4.8 measured
ARC-AGI-272.1%Not measuredOnly Claude Opus 4.8 measured
SimpleBench64.8%Not measuredOnly Claude Opus 4.8 measured
Chess puzzles52.0%20.0%Claude Opus 4.8
Mystery game puzzles36.0%18.0%Claude Opus 4.8
EBR-bench28.6%2.4%Claude Opus 4.8
LMArena Text: hard prompts14821470Claude Opus 4.8
LMArena Text: expert15031491Claude Opus 4.8
LMArena Text: hard prompts in English14871471Claude Opus 4.8
LMArena Vision: diagrams13151298Claude Opus 4.8
LMArena Vision: homework13371310Claude Opus 4.8
Kagi LLM Benchmark88.8%Not measuredOnly Claude Opus 4.8 measured
Neither model has a result on the other 4 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index60
Math benchmarks for Claude Opus 4.8 and Kimi K2.6
BenchmarkClaude Opus 4.8Kimi K2.6Leader
OTIS Mock AIME98.3%96.1%Claude Opus 4.8
FrontierMath, tiers 1 to 380.0%57.2%Claude Opus 4.8
FrontierMath, tier 456.1%25.6%Claude Opus 4.8
ProofBench69.0%16.0%Claude Opus 4.8
LMArena Text: math14861474Claude Opus 4.8
LMArena Text: mathematical work14971480Claude Opus 4.8
Neither model has a result on the other 7 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index92
Knowledge benchmarks for Claude Opus 4.8 and Kimi K2.6
BenchmarkClaude Opus 4.8Kimi K2.6Leader
MMLU Pro89.6%87.6%Claude Opus 4.8
LegalBench (Vals AI)83.6%84.7%Kimi K2.6
CaseLaw (Vals AI)Not measured61.2%Only Kimi K2.6 measured
CorpFin (Vals AI)66.7%66.7%Kimi K2.6
TaxEval (Vals AI)75.6%74.7%Claude Opus 4.8
MortgageTax (Vals AI)69.9%65.8%Claude Opus 4.8
MedCode (Vals AI)53.2%40.1%Claude Opus 4.8
SimpleQA Verified53.0%34.9%Claude Opus 4.8
LMArena Text: science14771468Claude Opus 4.8
LMArena Text: medicine and healthcare14641457Claude Opus 4.8
LMArena Text: legal and government14771462Claude Opus 4.8
LMArena Text: business and finance14581445Claude Opus 4.8
FACTS Benchmark Suite53.5%Not measuredOnly Claude Opus 4.8 measured
Neither model has a result on the other 5 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index35
Web design benchmarks for Claude Opus 4.8 and Kimi K2.6
BenchmarkClaude Opus 4.8Kimi K2.6Leader
Design Arena: websites12581268Kimi K2.6
Design Arena: UI components12551263Kimi K2.6
Design Arena: game dev12641250Claude Opus 4.8
Design Arena: data viz12401249Kimi K2.6
Design Arena: 3D12221267Kimi K2.6
Design Arena: all code categories12551271Kimi K2.6
Design Arena: SVG11951181Claude Opus 4.8
Design Arena: ASCII art12771165Claude Opus 4.8
LiveBench design78.8%Not measuredOnly Claude Opus 4.8 measured
GeneralLike-for-likePublic boards, shown as published, kept out of the index285
General benchmarks for Claude Opus 4.8 and Kimi K2.6
BenchmarkClaude Opus 4.8Kimi K2.6Leader
LiveBench data analysis66.0%Not measuredOnly Claude Opus 4.8 measured
Public Benefits Bench (Vals AI)68.1%56.6%Claude Opus 4.8
SAGE (Vals AI)54.8%50.2%Claude Opus 4.8
MedScribe (Vals AI)85.8%78.2%Claude Opus 4.8
Vals Multimodal Index70.9%56.4%Claude Opus 4.8
IFBench62.2%76.0%Kimi K2.6
Long context reasoning (AA-LCR)77.7%81.0%Kimi K2.6
DTBench94.9%90.9%Claude Opus 4.8
LMCA57.5%37.3%Claude Opus 4.8
Surface Evolver Bench87.5%Not measuredOnly Claude Opus 4.8 measured
Furniture assembly42.5%21.7%Claude Opus 4.8
ExploitBenchNot measured18.4%Only Kimi K2.6 measured
LMArena Text14611455Claude Opus 4.8
LMArena Text: instruction following14761451Claude Opus 4.8
LMArena Text: creative writing14541434Claude Opus 4.8
LMArena Vision12941282Claude Opus 4.8
LMArena Text: English14681460Claude Opus 4.8
LMArena Text: non-English14501446Claude Opus 4.8
LMArena Text: Chinese15061520Kimi K2.6
LMArena Text: German14721451Claude Opus 4.8
LMArena Text: Japanese14421443Kimi K2.6
LMArena Text: Korean14311427Claude Opus 4.8
LMArena Text: French14811471Claude Opus 4.8
LMArena Text: Spanish14651464Claude Opus 4.8
LMArena Text: Russian14741446Claude Opus 4.8
LMArena Text: Polish14591438Claude Opus 4.8
LMArena Text: multi-turn14761453Claude Opus 4.8
LMArena Text: longer queries14831468Claude Opus 4.8
LMArena Text: writing and language14611439Claude Opus 4.8
LMArena Text: entertainment and media14401428Claude Opus 4.8
LMArena Vision: English12931287Claude Opus 4.8
LMArena Vision: Chinese13461346Kimi K2.6
LMArena Vision: reading text13031291Claude Opus 4.8
LMArena Vision: humor12821280Claude Opus 4.8
LMArena Vision: creative writing13011273Claude Opus 4.8
LMArena Document14751451Claude Opus 4.8
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 4.8 and Kimi K2.6
BenchmarkClaude Opus 4.8Kimi 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 Opus 4.8$0.018Fits in one request
Kimi K2.6$0.0029Fits in one request

Kimi K2.6 costs less

Repository review

50K input + 3K output tokens

Claude Opus 4.8$0.325Fits in one request
Kimi K2.6$0.059Fits in one request

Kimi K2.6 costs less

Agent loop

200K input + 10K output tokens

Claude Opus 4.8$1.25Fits in one request
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 Opus 4.8 and Kimi K2.6
SpecificationAnthropic Claude Opus 4.8MoonshotAI Kimi K2.6
MakerAnthropicMoonshot AI
WeightsNo public weights listedOpen weights
ReleasedMay 27, 2026April 20, 2026
Context window1M262K
Input $/Mtok$5.00$0.95
Output $/Mtok$25.00$4.00
Coding index65.052.1
Independent measurements behind it63
Cost per solved task$2.17$0.35
SourceOpenRouter listingOpenRouter listing

Questions

Is Claude Opus 4.8 better than Kimi K2.6 for coding?

Pick Claude Opus 4.8 for coding: it scores 65.0 on the Vibe Coding Index against 52.1 for Kimi K2.6. Pick Kimi K2.6 for output tokens 6.3x cheaper ($4.00 vs $25.00 per million) and a lower cost per solved task ($0.35 against $2.17).

Which is cheaper, Claude Opus 4.8 or Kimi K2.6?

Claude Opus 4.8 costs $5.00 per million input tokens and $25.00 per million output tokens; Kimi K2.6 costs $0.95 and $4.00. Per solved SWE-bench Verified task, Claude Opus 4.8 costs $2.17 and Kimi K2.6 $0.35.

Which has the bigger context window, Claude Opus 4.8 or Kimi K2.6?

Claude Opus 4.8, with 1M tokens against 262K.

How many benchmarks is the Claude Opus 4.8 vs Kimi K2.6 comparison based on?

105 benchmarks have a result for both models as of October 22, 2026. Claude Opus 4.8's coding index rests on 6 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-opus-4-8-vs-kimi-k2-6" title="Claude Opus 4.8 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-opus-4-8-vs-kimi-k2-6">LLMBenchmark.ai, Claude Opus 4.8 vs Kimi K2.6</a></p>