Enter opens the highlighted result. Esc closes.

Claude Opus 4.8 vs Kimi K3

Updated October 21, 2026. 106 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.

Replace Claude Opus 4.8 Replace Kimi K3
Claude Opus 4.8Anthropic
Coding
66.0
Overall
41.8
Output $/M
$25.00
36
Kimi K3Moonshot AI
Coding
61.8
Overall
43.6
Output $/M
$11.936
70
vs boards won of 106 shared

Decision reading

Pick Claude Opus 4.8 for coding: it scores 66.0 on the Vibe Coding Index against 61.8 for Kimi K3.

Pick Kimi K3 when output tokens cost 2.1x less, or when a solved task costs $0.81 against $2.17.

Model AClaude Opus 4.8Anthropic66.0/1002 independent benchmarks$2.17 per solved taskModel BKimi K3Moonshot AI61.8/1002 independent benchmarks$0.81 per solved task
Shared results
106
Claude Opus 4.8 only
20
Kimi K3 only
11
Like-for-like categories
8 of 9

Shared results can support a head-to-head reading. Results only one model has describe coverage, not superiority.

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 66.0 from 2 benchmarks, Kimi K3 61.8 from 2 benchmarks.
Widest category
Web design, 11.9 points apart on average over 8 shared benchmarks.
Widest single gap
LiveBench browser: Claude Opus 4.8 96.0% against Kimi K3 16.0%, 80.0 points apart on a 0 to 100 scale.
Output price
Claude Opus 4.8 $25.00 against Kimi K3 $11.936 per million output tokens, 2.1x apart.
Context window
Claude Opus 4.8 takes 1M tokens, Kimi K3 1.05M.

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 K3Ties
Coding611
Intelligence11
Agentic work1110
Reasoning59
Math33
Knowledge47
Web design17
General522
All shared boards3670
CodingLike-for-likeFour of these boards feed the Vibe Coding Index611
Coding benchmarks for Claude Opus 4.8 and Kimi K3
BenchmarkClaude Opus 4.8Kimi K3Leader
LiveBench coding77.3%59.3%Claude Opus 4.8
LMArena WebDev15561655Kimi K3
AA Coding Index74.376.2Kimi K3
LiveCodeBench (Vals AI)87.8%87.2%Claude Opus 4.8
SWE-bench Verified (Vals AI)88.6%93.4%Kimi K3
Terminal-Bench 4 (Vals AI)23.2%17.2%Claude Opus 4.8
Vibe Code Bench (Vals AI)82.7%85.0%Kimi K3
Code migration (Vals AI)47.3%16.1%Claude Opus 4.8
ProgramBench (Vals AI)1.0%2.0%Kimi K3
IOI (Vals AI)Not measured48.9%Only Kimi K3 measured
Terminal-Bench 2.1 (Vals AI)71.9%80.9%Kimi K3
SWE-bench Multimodal (Vals AI)Not measured44.2%Only Kimi K3 measured
Vibe Code Bench 1-100 (Vals AI)Not measured18.2%Only Kimi K3 measured
SkillsBench (Vals AI)59.2%Not measuredOnly Claude Opus 4.8 measured
CyberBench (Vals AI)Not measured75.2%Only Kimi K3 measured
SciCode54.4%59.5%Kimi K3
Terminal-Bench Hard (Artificial Analysis run)58.3%Not measuredOnly Claude Opus 4.8 measured
FrontierCode46.5%44.2%Claude Opus 4.8
FrontierSWENot measured25.9%Only Kimi K3 measured
GSO-Bench47.1%Not measuredOnly Claude Opus 4.8 measured
WeirdML82.9%82.6%Claude Opus 4.8
ALE-BenchNot measured1524.5Only Kimi K3 measured
LMArena Text: coding14901508Kimi K3
LMArena Text: software and IT14881499Kimi K3
LMArena WebDev: React15571670Kimi K3
LMArena WebDev: HTML15431644Kimi K3
LMArena WebDev: from an imageNot measured1579Only Kimi K3 measured
Neither model has a result on the other 11 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index11
Intelligence benchmarks for Claude Opus 4.8 and Kimi K3
BenchmarkClaude Opus 4.8Kimi K3Leader
AA Intelligence Index41.843.6Kimi K3
Epoch Capabilities Index159.0157.9Claude Opus 4.8
Agentic workLike-for-likePublic boards, shown as published, kept out of the index1110
Agentic work benchmarks for Claude Opus 4.8 and Kimi K3
BenchmarkClaude Opus 4.8Kimi K3Leader
AA Agentic Index41.950.0Kimi K3
Design Arena: agents building web apps12331296Kimi K3
Design Arena: agents building full-stack apps12491315Kimi K3
Design Arena: agents building mobile apps12221267Kimi K3
Design Arena: agents building Android apps12371256Kimi K3
Design Arena: agents building Godot games12311223Claude Opus 4.8
Design Arena: agents building games12381252Kimi K3
Design Arena: HTML slides12211256Kimi K3
Design Arena: PowerPoint slides12271273Kimi K3
Design Arena: spreadsheetsNot measured1058Only Kimi K3 measured
LiveBench research81.8%79.0%Claude Opus 4.8
LiveBench browser96.0%16.0%Claude Opus 4.8
LiveBench long agentic48.3%42.8%Claude Opus 4.8
Finance Agent (Vals AI)53.9%53.1%Claude Opus 4.8
Tax Agent Bench (Vals AI)30.0%33.4%Kimi K3
Legal Research Bench (Vals AI)43.8%46.1%Kimi K3
Harvey's Legal Agent Benchmark (Vals AI)Not measured12.9%Only Kimi K3 measured
Excel Modeling Benchmark (Vals AI)69.4%66.7%Claude Opus 4.8
BioMysteryBench (Vals AI)Not measured72.6%Only Kimi K3 measured
Terminal-Bench-Science (Vals AI)4.3%1.4%Claude Opus 4.8
Time Horizon Index (Vals AI)11.8%10.5%Claude Opus 4.8
τ²-Bench Telecom94.4%Not measuredOnly Claude Opus 4.8 measured
APEX-Agents48.9%47.8%Claude Opus 4.8
Remote Labor Index8.3%Not measuredOnly Claude Opus 4.8 measured
OSWorld 2.020.6%Not measuredOnly Claude Opus 4.8 measured
DeepResearch Bench50.2%Not measuredOnly Claude Opus 4.8 measured
PostTrainBench33.8%32.0%Claude Opus 4.8
Vending-Bench 2$5,787$5,165Claude Opus 4.8
LMArena Search1204Not measuredOnly Claude Opus 4.8 measured
Neither model has a result on the other 10 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index59
Reasoning benchmarks for Claude Opus 4.8 and Kimi K3
BenchmarkClaude Opus 4.8Kimi K3Leader
GPQA Diamond92.4%92.9%Kimi K3
LiveBench reasoning89.2%90.7%Kimi K3
MMMU Pro (Vals AI)86.6%88.2%Kimi K3
GPQA Diamond (Artificial Analysis run)92.0%93.5%Kimi K3
Humanity's Last Exam (Artificial Analysis run)48.7%46.9%Claude Opus 4.8
GPQA Diamond (Epoch AI run)91.0%93.1%Kimi K3
ARC-AGI92.5%94.5%Kimi K3
ARC-AGI-272.1%60.4%Claude Opus 4.8
SimpleBench64.8%60.7%Claude Opus 4.8
Chess puzzles52.0%37.0%Claude Opus 4.8
Mystery game puzzles36.0%26.0%Claude Opus 4.8
EBR-bench28.6%Not measuredOnly Claude Opus 4.8 measured
LMArena Text: hard prompts14821495Kimi K3
LMArena Text: expert15031520Kimi K3
LMArena Text: hard prompts in English14871496Kimi K3
LMArena Vision: diagrams1315Not measuredOnly Claude Opus 4.8 measured
LMArena Vision: homework1337Not 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 index33
Math benchmarks for Claude Opus 4.8 and Kimi K3
BenchmarkClaude Opus 4.8Kimi K3Leader
OTIS Mock AIME98.3%97.2%Claude Opus 4.8
FrontierMath, tiers 1 to 380.0%72.2%Claude Opus 4.8
FrontierMath, tier 456.1%39.0%Claude Opus 4.8
ProofBench69.0%87.0%Kimi K3
LMArena Text: math14861494Kimi K3
LMArena Text: mathematical work14971505Kimi K3
Neither model has a result on the other 7 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index47
Knowledge benchmarks for Claude Opus 4.8 and Kimi K3
BenchmarkClaude Opus 4.8Kimi K3Leader
MMLU Pro89.6%88.0%Claude Opus 4.8
LegalBench (Vals AI)83.6%86.2%Kimi K3
CorpFin (Vals AI)66.7%71.6%Kimi K3
TaxEval (Vals AI)75.6%75.7%Kimi K3
MortgageTax (Vals AI)69.9%66.3%Claude Opus 4.8
MedCode (Vals AI)53.2%49.4%Claude Opus 4.8
SimpleQA Verified53.0%50.6%Claude Opus 4.8
LMArena Text: science14771508Kimi K3
LMArena Text: medicine and healthcare14641489Kimi K3
LMArena Text: legal and government14771503Kimi K3
LMArena Text: business and finance14581470Kimi K3
Neither model has a result on the other 6 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index17
Web design benchmarks for Claude Opus 4.8 and Kimi K3
BenchmarkClaude Opus 4.8Kimi K3Leader
Design Arena: websites12581336Kimi K3
Design Arena: UI components12561345Kimi K3
Design Arena: game dev12641361Kimi K3
Design Arena: data viz12401350Kimi K3
Design Arena: 3D12231388Kimi K3
Design Arena: all code categories12551361Kimi K3
Design Arena: SVG11941301Kimi K3
Design Arena: ASCII art1276Not measuredOnly Claude Opus 4.8 measured
LiveBench design78.8%77.2%Claude Opus 4.8
GeneralLike-for-likePublic boards, shown as published, kept out of the index522
General benchmarks for Claude Opus 4.8 and Kimi K3
BenchmarkClaude Opus 4.8Kimi K3Leader
Vals IndexNot measured53.0%Only Kimi K3 measured
LiveBench data analysis66.0%78.7%Kimi K3
Public Benefits Bench (Vals AI)68.1%68.2%Kimi K3
SAGE (Vals AI)54.8%52.8%Claude Opus 4.8
MedScribe (Vals AI)85.8%88.0%Kimi K3
Vals Multimodal Index70.9%73.4%Kimi K3
IFBench62.2%Not measuredOnly Claude Opus 4.8 measured
Long context reasoning (AA-LCR)77.7%88.7%Kimi K3
DTBench94.9%91.2%Claude Opus 4.8
LMCA57.5%52.7%Claude Opus 4.8
Surface Evolver Bench87.5%95.0%Kimi K3
Furniture assembly42.5%34.2%Claude Opus 4.8
LMArena Text14611476Kimi K3
LMArena Text: instruction following14761485Kimi K3
LMArena Text: creative writing14541457Kimi K3
LMArena Vision1294Not measuredOnly Claude Opus 4.8 measured
LMArena Text: English14681481Kimi K3
LMArena Text: non-English14501466Kimi K3
LMArena Text: Chinese15061529Kimi K3
LMArena Text: German14721490Kimi K3
LMArena Text: Japanese14421494Kimi K3
LMArena Text: Korean14311460Kimi K3
LMArena Text: French14811492Kimi K3
LMArena Text: Spanish14651472Kimi K3
LMArena Text: Russian14741485Kimi K3
LMArena Text: Polish14591458Claude Opus 4.8
LMArena Text: multi-turn14761489Kimi K3
LMArena Text: longer queries14831494Kimi K3
LMArena Text: writing and language14611471Kimi K3
LMArena Text: entertainment and media14401453Kimi K3
LMArena Vision: English1293Not measuredOnly Claude Opus 4.8 measured
LMArena Vision: Chinese1346Not measuredOnly Claude Opus 4.8 measured
LMArena Vision: reading text1303Not measuredOnly Claude Opus 4.8 measured
LMArena Vision: humor1282Not measuredOnly Claude Opus 4.8 measured
LMArena Vision: creative writing1301Not measuredOnly Claude Opus 4.8 measured
LMArena Document1475Not measuredOnly Claude Opus 4.8 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 4.8 and Kimi K3
BenchmarkClaude Opus 4.8Kimi K3Leader
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 K3$0.0062Fits in one request

Kimi K3 costs less

Repository review

50K input + 3K output tokens

Claude Opus 4.8$0.325Fits in one request
Kimi K3$0.048Fits in one request

Kimi K3 costs less

Agent loop

200K input + 10K output tokens

Claude Opus 4.8$1.25Fits in one request
Kimi K3$0.167Fits in one request

Kimi K3 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 K3
SpecificationAnthropic Claude Opus 4.8MoonshotAI Kimi K3
MakerAnthropicMoonshot AI
WeightsNo public weights listedOpen weights
ReleasedMay 27, 2026July 16, 2026
Context window1M1.05M
Input $/Mtok$5.00$0.239
Output $/Mtok$25.00$11.936
Coding index66.061.8
Independent measurements behind it22
Cost per solved task$2.17$0.81
SourceOpenRouter listingOpenRouter listing

Questions

Is Claude Opus 4.8 better than Kimi K3 for coding?

Pick Claude Opus 4.8 for coding: it scores 66.0 on the Vibe Coding Index against 61.8 for Kimi K3. Pick Kimi K3 when output tokens cost 2.1x less, or when a solved task costs $0.81 against $2.17.

Which is cheaper, Claude Opus 4.8 or Kimi K3?

Claude Opus 4.8 costs $5.00 per million input tokens and $25.00 per million output tokens; Kimi K3 costs $0.239 and $11.936. Per solved SWE-bench Verified task, Claude Opus 4.8 costs $2.17 and Kimi K3 $0.81.

Which has the bigger context window, Claude Opus 4.8 or Kimi K3?

Kimi K3, with 1.05M tokens against 1M.

How many benchmarks is the Claude Opus 4.8 vs Kimi K3 comparison based on?

106 benchmarks have a result for both models as of October 21, 2026. Claude Opus 4.8's coding index rests on 2 independent benchmarks and Kimi K3's on 2. 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-k3" title="Claude Opus 4.8 vs Kimi K3, 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-k3">LLMBenchmark.ai, Claude Opus 4.8 vs Kimi K3</a></p>