Head-to-head comparison

Claude Opus 4.8 vs. Kimi K3

Compare published benchmark results from matching versions and cohorts, API pricing, and technical specifications. Any documented test setup differences remain visible.

shared result series: 208
distinct benchmark metrics: 28
latest retrieval: 2026-10-16

First modelSecond model

Specifications

General specifications

Release date, availability, context window, architecture, and published parameter counts at a glance. Undisclosed details remain marked as unavailable.

Specifications for Claude Opus 4.8 and Kimi K3
Attribute	Claude Opus 4.8	Kimi K3
Provider	Anthropic	Moonshot AI
Released	May 2026	Jul 16, 2026
Availability	Legacy	Active
Model type	Proprietary	Open Weights
Parameters	Not published	2.8T, 104B active
Architecture	Not published	Mixture of Experts
Context window	1,000,000 tokens	1,048,576 tokens
Knowledge cutoff	January 2026	Not published
Technical sources	Model, Knowledge cutoff	Model

Pricing

API pricing compared

The table compares official standard API rates per 1M tokens, including published cache pricing. Batch, fast, priority, regional surcharges, tool calls, and cloud platform pricing are excluded.

API pricing for Claude Opus 4.8 and Kimi K3
Price type	Claude Opus 4.8	Kimi K3
API input	$5	$3
API output	$25	$15
Cache read	$0.5	$0.3
Cache write (5 min.)	$6.25	Not listed
Cache write (1 hr.)	$10	Not listed
Price verified	09/22/2026 Source	09/22/2026 Source

Claude Opus 4.8Kimi K3

API inputUSD per 1M tokens, base tier

Claude Opus 4.8$5

Kimi K3$3

API outputUSD per 1M tokens, base tier

Claude Opus 4.8$25

Kimi K3$15

Cache readUSD per 1M tokens, base tier

Claude Opus 4.8$0.5

Kimi K3$0.3

Key to the marks:better valuebetter, but not conclusivetie

Pricing by provider

Direct developer pricing and provider endpoint tariffs routed through OpenRouter are listed separately. Prices are in USD per 1M tokens. Context-dependent direct tiers plus regional, Flex, Priority, and other OpenRouter tariffs remain individually identifiable.

No provider tariff for Claude Opus 4.8 is available in the stored OpenRouter snapshot. The official direct price is still shown.

Provider pricing for Claude Opus 4.8 and Kimi K3
Model	Provider	Purchase route and tariff	Input per 1M tokens	Output per 1M tokens	Source
Claude Opus 4.8	Anthropic	Direct from developerStandard API	Lowest listed price: $5	Lowest listed price: $25	Source09/22/2026
Kimi K3	Moonshot AI	Direct from developerStandard API	$3	$15	Source09/22/2026
	AkashML	Via OpenRouterakashml/fp4	$1.2	$14	Source10/26/2026
	Alibaba	Via OpenRouteralibaba	$3.45	$17.25	Source10/26/2026
	Amazon Bedrock	Via OpenRouteramazon-bedrock/us-east-2	$3	$15	Source10/26/2026
	BaseTen	Via OpenRouterbaseten/fp8	$3	$15	Source10/26/2026
	Chutes	Via OpenRouterchutes/mxfp4	$1.85	$9.5	Source10/26/2026
	Decart	Via OpenRouterdecart/mxfp4	$1.65	$8.25	Source10/26/2026
	DeepInfra	Via OpenRouterdeepinfra/mxfp4	$2.85	$14.25	Source10/26/2026
	DigitalOcean	Via OpenRouterdigitalocean	$2.55	$12.95	Source10/26/2026
	Fireworks	Via OpenRouterfireworks	$3	$15	Source10/26/2026
	Fireworks	Via OpenRouterfireworks/fast	$4.5	$22.5	Source10/26/2026
	Fireworks	Via OpenRouterfireworks/us	$4.5	$22.5	Source10/26/2026
	InferenceNet	Via OpenRouterinference-net/fast	$0.5	$11.88	Source10/26/2026
	InferenceNet	Via OpenRouterinference-net/fp4	$0.239	$10.8	Source10/26/2026
	InferenceNet	Via OpenRouterinference-net/us	$0.239	$10.8	Source10/26/2026
	InferenceNet	Via OpenRouterinference-net/us/fast	$2.24	$14.519	Source10/26/2026
	Makora	Via OpenRoutermakora/fp4	$0.65	$15	Source10/26/2026
	Modal	Via OpenRoutermodal/mxfp4	$3	$15	Source10/26/2026
	Moonshot AI	Via OpenRoutermoonshotai/mxfp4	$3	$15	Source10/26/2026
	Morph	Via OpenRoutermorph/fp8	$1.17	$18.769	Source10/26/2026
	Parasail	Via OpenRouterparasail/fp4	$3	$15	Source10/26/2026
	ParetoAlpha	Via OpenRouterpareto-alpha/us	$3	$15	Source10/26/2026
	Phala	Via OpenRouterphala	$2.55	$12.75	Source10/26/2026
	Relace	Via OpenRouterrelace/fp4	Lowest listed price: $0.2147	$7.6972	Source10/26/2026
	Sail Research	Via OpenRoutersail-research/fp4	$1.2	Lowest listed price: $5.5	Source10/26/2026
	Sail Research	Via OpenRoutersail-research/fp4/us	$1.2	Lowest listed price: $5.5	Source10/26/2026
	Wafer	Via OpenRouterwafer	$0.226	$20	Source10/26/2026
	Wafer	Via OpenRouterwafer/us	$0.36	$11.9	Source10/26/2026

Benchmark index

Benchmark index compared

The index combines independent benchmarks on a scale from 0 to 100. A lead only counts when a model comes first in at least 95% of 200 recalculations with randomly redrawn test families. Otherwise both count as level.

Open the AI leaderboard

Claude Opus 4.8

Overall index

57.0tied

Kimi K3

Overall index

62.0tied

Kimi K3 leads in 2 of 11 shared areas. 8 areas are tied.

Area	Claude Opus 4.8	Kimi K3
Codingtied	55.3	52.2
Reasoningtied	46.2	64.0
Knowledge	65.6	49.3
Agentstied	56.7	61.7
General	45.3	69.5
Financetied	65.0	70.3
Legal	57.4	73.4
Healthtied	67.8	68.9
Multimodaltied	55.0	56.3
Productivitytied	68.3	69.6
Educationtied	71.1	69.5

Performance

Shared benchmarks

Only published results with the same benchmark version, task, metric, and comparison cohort are paired. Different reasoning levels, agents, harnesses, or output limits appear directly in the table.

Capability profile from matched benchmarks

Each axis averages directly matched benchmark families. A value of 100 means the stronger value within this pair, not a universal quality score.

Not enough directly matched categories for a reliable radar

Only 1 of at least 5 categories have comparable, direct model measurements. The benchmark tables below show the available evidence without filling missing axes.

Claude Opus 4.8Kimi K3

Code MigrationOverall. Higher is better. Test setup not documented as identical

Claude Opus 4.847.25 %

Kimi K316.099 %

CorpFin v2Overall. Higher is better. Test setup not documented as identical

Claude Opus 4.866.706 %

Kimi K371.562 %

EMBOverall. Higher is better. Test setup not documented as identical

Claude Opus 4.869.373 %

Kimi K366.677 %

Finance Agent (v2)Overall. Higher is better. Test setup not documented as identical

Claude Opus 4.853.918 %

Kimi K353.114 %

GPQA DiamondOverall. Higher is better. Test setup not documented as identical

Claude Opus 4.892.424 %

Kimi K392.929 %

Harvey's Legal Agent BenchmarkOverall · Task fully resolved. Higher is better. Test setup not documented as identical

Claude Opus 4.89.583 %

Kimi K312.917 %

Legal Research BenchOverall · All-pass. Higher is better. Test setup not documented as identical

Claude Opus 4.843.75 %

Kimi K346.154 %

LegalBenchOverall. Higher is better. Test setup not documented as identical

Claude Opus 4.883.568 %

Kimi K386.212 %

LiveCodeBench v6Overall. Higher is better. Test setup not documented as identical

Claude Opus 4.887.819 %

Kimi K387.185 %

LMArena Code Arena WebDevOverall. Higher is better. Test setup not documented as identical

Claude Opus 4.81,536.177

Kimi K31,655.295

MedCodeOverall. Higher is better. Test setup not documented as identical

Claude Opus 4.853.217 %

Kimi K349.357 %

MedScribeOverall. Higher is better. Test setup not documented as identical

Claude Opus 4.885.755 %

Kimi K388.048 %

Key to the marks:better valuebetter, but not conclusivetie

Benchmark scores for Claude Opus 4.8 and Kimi K3
Benchmark and task	Claude Opus 4.8	Kimi K3	Source
Code MigrationOverall Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens Kimi K3: Reasoning: max, Temperature: 1, Top P: 0.95, Output limit: 262,144 tokens	Higher measured value47.25 %	16.099 %	Vals AI Source details Data as of: 10/12/2026
CorpFin v2Overall Test details Test setup not documented as identicalNo direct winnerVersion: 2Metric: accuracyScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens Kimi K3: Temperature: 1, Output limit: 262,144 tokens	66.706 %	Higher measured value71.562 %	Vals AI Source details Data as of: 08/12/2026
EMBOverall Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens Kimi K3: Reasoning: max, Temperature: 1, Top P: 0.95, Output limit: 262,144 tokens	Higher measured value69.373 %	66.677 %	Vals AI Source details Data as of: 10/12/2026
Finance Agent (v2)Overall Test details Test setup not documented as identicalNo direct winnerVersion: 2Metric: accuracyScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens Kimi K3: Reasoning: max, Temperature: 1, Top P: 0.95, Output limit: 262,144 tokens	Higher measured value53.918 %	53.114 %	Vals AI Source details Data as of: 10/12/2026
GPQA DiamondOverall Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens Kimi K3: Temperature: 1, Output limit: 262,144 tokens	92.424 %	Higher measured value92.929 %	Vals AI Source details Data as of: 09/01/2026
Harvey's Legal Agent BenchmarkOverall · Task fully resolved Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: task resolution rateScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens Kimi K3: Reasoning: max, Temperature: 1, Top P: 0.95, Output limit: 262,144 tokens	9.583 %	Higher measured value12.917 %	Vals AI Source details Data as of: 10/12/2026
Legal Research BenchOverall · All-pass Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: all-pass rateScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens Kimi K3: Reasoning: max, Temperature: 1, Top P: 0.95, Output limit: 262,144 tokens	43.75 %	Higher measured value46.154 %	Vals AI Source details Data as of: 10/12/2026
LegalBenchOverall Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens Kimi K3: Reasoning: max, Temperature: 1, Top P: 0.95, Output limit: 262,144 tokens	83.568 %	Higher measured value86.212 %	Vals AI Source details Data as of: 10/13/2026
LiveCodeBench v6Overall Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens Kimi K3: Reasoning: max, Output limit: 262,144 tokens	Higher measured value87.819 %	87.185 %	Vals AI Source details Data as of: 09/01/2026
LMArena Code Arena WebDevOverall Test details Test setup not documented as identicalNo direct winnerVersion: webdevMetric: WebDev Arena Bradley-Terry ratingScoring: Higher is betterClaude Opus 4.8: Snapshot: claude-opus-4-8, Harness: Arena Code Arena WebDev Kimi K3: Snapshot: kimi-k3-max, Reasoning: max, Harness: Arena Code Arena WebDevClaude Opus 4.8: Arena rating from 17,454 published pairwise votes.Kimi K3: Arena rating from 18,644 published pairwise votes.	1,536.177 95% confidence interval: ±5.702The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.	Higher measured value1,655.295 95% confidence interval: ±6.069The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.	LMArena Source details Data as of: 10/13/2026
MedCodeOverall Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 30,000 tokens Kimi K3: Reasoning: max, Temperature: 1, Top P: 0.95, Output limit: 262,144 tokens	Higher measured value53.217 %	49.357 %	Vals AI Source details Data as of: 10/13/2026
MedScribeOverall Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 30,000 tokens Kimi K3: Reasoning: max, Temperature: 1, Top P: 0.95, Output limit: 262,144 tokens	85.755 %	Higher measured value88.048 %	Vals AI Source details Data as of: 10/13/2026
MMLU-ProOverall Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens Kimi K3: Reasoning: max, Output limit: 262,144 tokens	Higher measured value89.585 %	87.973 %	Vals AI Source details Data as of: 09/01/2026
MMMU-ProOverall Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens Kimi K3: Temperature: 1, Output limit: 262,144 tokens	86.59 %	Higher measured value88.15 %	Vals AI Source details Data as of: 09/01/2026
MortgageTaxOverall Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens Kimi K3: Temperature: 1, Output limit: 262,144 tokens	Higher measured value69.912 %	66.336 %	Vals AI Source details Data as of: 09/01/2026
ProgramBenchOverall Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: fully resolved rateScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens Kimi K3: Temperature: 1, Output limit: 262,144 tokens	1 %	Higher measured value2 %	Vals AI Source details Data as of: 10/12/2026
Public Benefits Bench v1.1Overall Test details Test setup not documented as identicalNo direct winnerVersion: 1.1Metric: accuracyScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens Kimi K3: Reasoning: max, Temperature: 1, Top P: 0.95, Output limit: 262,144 tokens	68.133 %	Higher measured value68.2 %	Vals AI Source details Data as of: 10/12/2026
SAGEOverall Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 30,000 tokens Kimi K3: Reasoning: max, Temperature: 1, Top P: 0.95, Output limit: 262,144 tokens	Higher measured value54.788 %	52.783 %	Vals AI Source details Data as of: 10/08/2026
SWE-bench VerifiedOverall Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens Kimi K3: Temperature: 1, Output limit: 262,144 tokens	88.6 %	Higher measured value93.4 %	Vals AI Source details Data as of: 09/01/2026
Tax Agent BenchOverall Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens Kimi K3: Reasoning: max, Temperature: 1, Top P: 0.95, Output limit: 262,144 tokens	29.999 %	Higher measured value33.368 %	Vals AI Source details Data as of: 10/12/2026
TaxEval v2Overall Test details Test setup not documented as identicalNo direct winnerVersion: 2Metric: accuracyScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens Kimi K3: Temperature: 1, Output limit: 262,144 tokens	75.634 %	Higher measured value75.716 %	Vals AI Source details Data as of: 09/01/2026
Terminal-Bench 2.1Overall Test details Test setup not documented as identicalNo direct winnerVersion: 2.1Metric: accuracyScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens Kimi K3: Temperature: 1, Output limit: 262,144 tokens	71.91 %	Higher measured value80.899 %	Vals AI Source details Data as of: 09/28/2026
Terminal-Bench 4.0Overall Test details Test setup not documented as identicalNo direct winnerVersion: 4.0Metric: accuracyScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens Kimi K3: Reasoning: max, Temperature: 1, Top P: 0.95, Output limit: 262,144 tokens	Higher measured value23.232 %	17.172 %	Vals AI Source details Data as of: 10/13/2026
Terminal-Bench ScienceOverall Test details Test setup not documented as identicalNo direct winnerVersion: 0.1Metric: accuracyScoring: Higher is betterClaude Opus 4.8: Compute: max, Harness: Mini-SWE-agent, Temperature: 1, Output limit: 128,000 tokens Kimi K3: Reasoning: max, Harness: Mini-SWE-agent, Temperature: 1, Top P: 0.95, Output limit: 262,144 tokens	Higher measured value4.286 %	1.429 %	Vals AI Source details Data as of: 10/14/2026
Time Horizon Index: KSPOverall Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: progressScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens Kimi K3: Reasoning: max, Temperature: 1, Top P: 0.95, Output limit: 262,144 tokens	Higher measured value11.833 %	10.5 %	Vals AI Source details Data as of: 10/07/2026
Vals IndexOverall Test details Test setup not documented as identicalNo direct winnerVersion: 2.1Metric: weighted index scoreScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens Kimi K3: Reasoning: max, Temperature: 1, Top P: 0.95, Output limit: 262,144 tokens	Higher measured value55.1 %	50.297 %	Vals AI Source details Data as of: 10/13/2026
Vals Multimodal IndexOverall Test details Test setup not documented as identicalNo direct winnerVersion: 1.2Metric: weighted index scoreScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens Kimi K3: Temperature: 1, Output limit: 262,144 tokens	70.889 %	Higher measured value73.42 %	Vals AI Source details Data as of: 08/11/2026
Vibe Code Bench v1.1Overall Test details Test setup not documented as identicalNo direct winnerVersion: 1.1Metric: accuracyScoring: Higher is betterClaude Opus 4.8: Compute: max, Harness: OpenHands, Temperature: 1, Output limit: 128,000 tokens Kimi K3: Reasoning: max, Harness: OpenHands, Temperature: 1, Top P: 0.95, Output limit: 262,144 tokens	82.725 %	Higher measured value84.968 %	Vals AI Source details Data as of: 10/12/2026
Code MigrationCLI Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens Kimi K3: Reasoning: max, Temperature: 1, Top P: 0.95, Output limit: 262,144 tokens	Higher measured value40.143 %	1.465 %	Vals AI Source details Data as of: 10/12/2026
CorpFin v2Exact Pages Test details Test setup not documented as identicalNo direct winnerVersion: 2Metric: accuracyScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens Kimi K3: Temperature: 1, Output limit: 262,144 tokens	64.336 %	Higher measured value69.347 %	Vals AI Source details Data as of: 08/12/2026
EMBComps Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens Kimi K3: Reasoning: max, Temperature: 1, Top P: 0.95, Output limit: 262,144 tokens	Higher measured value72.797 %	70.837 %	Vals AI Source details Data as of: 10/12/2026
Finance Agent (v2)Adjustments Test details Test setup not documented as identicalNo direct winnerVersion: 2Metric: accuracyScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens Kimi K3: Reasoning: max, Temperature: 1, Top P: 0.95, Output limit: 262,144 tokens	Higher measured value48.387 %	45.274 %	Vals AI Source details Data as of: 10/12/2026
GPQA DiamondFew-Shot CoT Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens Kimi K3: Temperature: 1, Output limit: 262,144 tokens	91.919 %	Higher measured value93.434 %	Vals AI Source details Data as of: 09/01/2026
Harvey's Legal Agent BenchmarkAntitrust Competition · Criteria passed Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: criteria pass rateScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens Kimi K3: Reasoning: max, Temperature: 1, Top P: 0.95, Output limit: 262,144 tokens	87.319 %	Higher measured value88.768 %	Vals AI Source details Data as of: 10/12/2026
Legal Research BenchAdministrative / Regulatory · All-pass Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: all-pass rateScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens Kimi K3: Reasoning: max, Temperature: 1, Top P: 0.95, Output limit: 262,144 tokens	43.939 %	Higher measured value63.636 %	Vals AI Source details Data as of: 10/12/2026
LegalBenchConclusion Tasks Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens Kimi K3: Reasoning: max, Temperature: 1, Top P: 0.95, Output limit: 262,144 tokens	88.937 %	Higher measured value90.076 %	Vals AI Source details Data as of: 10/13/2026
LiveCodeBench v6Easy Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens Kimi K3: Reasoning: max, Output limit: 262,144 tokens	Higher measured value99.068 %	98.758 %	Vals AI Source details Data as of: 09/01/2026
LMArena Code Arena WebDevOverall Test details Test setup not documented as identicalNo direct winnerVersion: webdevMetric: WebDev Arena Bradley-Terry ratingScoring: Higher is betterClaude Opus 4.8: Snapshot: claude-opus-4-8-high, Reasoning: high, Harness: Arena Code Arena WebDev Kimi K3: Snapshot: kimi-k3-max, Reasoning: max, Harness: Arena Code Arena WebDevClaude Opus 4.8: Arena rating from 18,540 published pairwise votes.Kimi K3: Arena rating from 18,644 published pairwise votes.	1,555.99 95% confidence interval: ±5.768The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.	Higher measured value1,655.295 95% confidence interval: ±6.069The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.	LMArena Source details Data as of: 10/13/2026
MMLU-ProBiology Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens Kimi K3: Reasoning: max, Output limit: 262,144 tokens	Higher measured value94.7 %	93.863 %	Vals AI Source details Data as of: 09/01/2026
MortgageTaxNumerical Extraction Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens Kimi K3: Temperature: 1, Output limit: 262,144 tokens	Higher measured value79.73 %	78.855 %	Vals AI Source details Data as of: 09/01/2026
ProgramBenchAlmost Resolved Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: almost-resolved rateScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens Kimi K3: Temperature: 1, Output limit: 262,144 tokens	15.5 %	Higher measured value17.5 %	Vals AI Source details Data as of: 10/12/2026
SAGEAutomata Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 30,000 tokens Kimi K3: Reasoning: max, Temperature: 1, Top P: 0.95, Output limit: 262,144 tokens	41.666 %	Higher measured value43.254 %	Vals AI Source details Data as of: 10/08/2026
SWE-bench Verified<15 min fix Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens Kimi K3: Temperature: 1, Output limit: 262,144 tokens	Higher measured value92.784 %	92.268 %	Vals AI Source details Data as of: 09/01/2026
Tax Agent BenchControversy & Precedence Analysis Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens Kimi K3: Reasoning: max, Temperature: 1, Top P: 0.95, Output limit: 262,144 tokens	13.133 %	Higher measured value13.333 %	Vals AI Source details Data as of: 10/12/2026
TaxEval v2Correctness Test details Test setup not documented as identicalNo direct winnerVersion: 2Metric: accuracyScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens Kimi K3: Temperature: 1, Output limit: 262,144 tokens	64.513 %	Higher measured value65.331 %	Vals AI Source details Data as of: 09/01/2026
Terminal-Bench 2.1Easy Test details Test setup not documented as identicalNo direct winnerVersion: 2.1Metric: accuracyScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens Kimi K3: Temperature: 1, Output limit: 262,144 tokens	Higher measured value100 %	91.667 %	Vals AI Source details Data as of: 09/28/2026
Terminal-Bench 4.0Hardware Test details Test setup not documented as identicalNo direct winnerVersion: 4.0Metric: accuracyScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens Kimi K3: Reasoning: max, Temperature: 1, Top P: 0.95, Output limit: 262,144 tokens	Higher measured value26.667 %	13.333 %	Vals AI Source details Data as of: 10/13/2026
Terminal-Bench ScienceEarth Sciences Test details Test setup not documented as identicalNo direct winnerVersion: 0.1Metric: accuracyScoring: Higher is betterClaude Opus 4.8: Compute: max, Harness: Mini-SWE-agent, Temperature: 1, Output limit: 128,000 tokens Kimi K3: Reasoning: max, Harness: Mini-SWE-agent, Temperature: 1, Top P: 0.95, Output limit: 262,144 tokens	0 %	Higher measured value12.5 %	Vals AI Source details Data as of: 10/14/2026
Time Horizon Index: KSPProgress efficiency Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: progressScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens Kimi K3: Reasoning: max, Temperature: 1, Top P: 0.95, Output limit: 262,144 tokens	7.739 %	Higher measured value9.258 %	Vals AI Source details Data as of: 10/07/2026
Vals IndexCode Migration Test details Test setup not documented as identicalNo direct winnerVersion: 2.1Metric: benchmark scoreScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens Kimi K3: Reasoning: max, Temperature: 1, Top P: 0.95, Output limit: 262,144 tokens	Higher measured value46.942 %	16.042 %	Vals AI Source details Data as of: 10/13/2026
Vals Multimodal IndexCorpFin v2 Test details Test setup not documented as identicalNo direct winnerVersion: 1.2Metric: benchmark scoreScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens Kimi K3: Temperature: 1, Output limit: 262,144 tokens	65.967 %	Higher measured value72.611 %	Vals AI Source details Data as of: 08/11/2026
Code MigrationCOBOL Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens Kimi K3: Reasoning: max, Temperature: 1, Top P: 0.95, Output limit: 262,144 tokens	Higher measured value68.571 %	60 %	Vals AI Source details Data as of: 10/12/2026
CorpFin v2Max Fitting Context Test details Test setup not documented as identicalNo direct winnerVersion: 2Metric: accuracyScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens Kimi K3: Temperature: 1, Output limit: 262,144 tokens	69.814 %	Higher measured value72.727 %	Vals AI Source details Data as of: 08/12/2026
EMBDataroom Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens Kimi K3: Reasoning: max, Temperature: 1, Top P: 0.95, Output limit: 262,144 tokens	Higher measured value85.948 %	82.661 %	Vals AI Source details Data as of: 10/12/2026
Finance Agent (v2)All-Pass Test details Test setup not documented as identicalNo direct winnerVersion: 2Metric: accuracyScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens Kimi K3: Reasoning: max, Temperature: 1, Top P: 0.95, Output limit: 262,144 tokens	Higher measured value43.517 %	41.837 %	Vals AI Source details Data as of: 10/12/2026
GPQA DiamondZero-Shot CoT Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens Kimi K3: Temperature: 1, Output limit: 262,144 tokens	Higher measured value92.929 %	92.424 %	Vals AI Source details Data as of: 09/01/2026
Harvey's Legal Agent BenchmarkAntitrust Competition · Task fully resolved Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: task resolution rateScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens Kimi K3: Reasoning: max, Temperature: 1, Top P: 0.95, Output limit: 262,144 tokens	0 %	Higher measured value20 %	Vals AI Source details Data as of: 10/12/2026
Legal Research BenchAdministrative / Regulatory · Weighted partial credit Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: weighted partial-credit scoreScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens Kimi K3: Reasoning: max, Temperature: 1, Top P: 0.95, Output limit: 262,144 tokens	87.365 %	Higher measured value89.252 %	Vals AI Source details Data as of: 10/12/2026
LegalBenchInterpretation Tasks Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens Kimi K3: Reasoning: max, Temperature: 1, Top P: 0.95, Output limit: 262,144 tokens	82.703 %	Higher measured value84.092 %	Vals AI Source details Data as of: 10/13/2026
LiveCodeBench v6Hard Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens Kimi K3: Reasoning: max, Output limit: 262,144 tokens	Higher measured value74.571 %	74.286 %	Vals AI Source details Data as of: 09/01/2026
LMArena Code Arena WebDevWebdev Test details Test setup not documented as identicalNo direct winnerVersion: webdevMetric: WebDev Arena Bradley-Terry ratingScoring: Higher is betterClaude Opus 4.8: Snapshot: claude-opus-4-8, Harness: Arena Code Arena WebDev Kimi K3: Snapshot: kimi-k3-max, Reasoning: max, Harness: Arena Code Arena WebDevClaude Opus 4.8: Arena rating from 17,454 published pairwise votes.Kimi K3: Arena rating from 18,644 published pairwise votes.	1,536.177 95% confidence interval: ±5.702The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.	Higher measured value1,655.295 95% confidence interval: ±6.069The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.	LMArena Source details Data as of: 10/13/2026
MMLU-ProBusiness Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens Kimi K3: Reasoning: max, Output limit: 262,144 tokens	Higher measured value92.649 %	92.015 %	Vals AI Source details Data as of: 09/01/2026
MortgageTaxSemantic Extraction Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens Kimi K3: Temperature: 1, Output limit: 262,144 tokens	Higher measured value60.095 %	53.816 %	Vals AI Source details Data as of: 09/01/2026
ProgramBenchFully Resolved Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: fully resolved rateScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens Kimi K3: Temperature: 1, Output limit: 262,144 tokens	1 %	Higher measured value2 %	Vals AI Source details Data as of: 10/12/2026
Key to the marks:better valuebetter, but not conclusivetie

Our model tests

Our tests

SVG short test

One SVG prompt and fixed output settings. Captures are shown only with 0 reported reasoning tokens or documented lack of reasoning controls. Identical test conditions do not make the models' internal compute identical.

Shared test round: 43b8c5c46830

Claude Opus 4.8

Unavailable in this round

Kimi K3

Earlier tests

Pelican on a bicycle

A community classic for free-form SVG drawing.

Claude Opus 4.8

Reasoning (requested): high

Current attempt

Run date: Oct 1, 2026
API provider: openrouter
Requested API model: anthropic/claude-opus-4.8
API model reported in response: anthropic/claude-opus-4.8
Reasoning setting: high
Pinned endpoint: Anthropic | anthropic/claude-4.8-opus-20260528
Temperature: Provider default
Token limit including reasoning: 8,192 tokens
Test protocol: community-visual-tests-v1
Technical checks: Passed, not a quality rating
Response time: 18 s

Visually reviewed. This individual test does not establish overall model quality.

Kimi K3

Reasoning (requested): high

Current attempt

Run date: Oct 1, 2026
API provider: openrouter
Requested API model: moonshotai/kimi-k3
API model reported in response: moonshotai/kimi-k3
Reasoning setting: high
Pinned endpoint: Moonshot AI | moonshotai/kimi-k3-20260715
Temperature: Provider default
Token limit including reasoning: 8,192 tokens
Test protocol: community-visual-tests-v1
Technical checks: Passed, not a quality rating
Response time: 173.4 s

Visually reviewed. This individual test does not establish overall model quality.

Earlier attempts (1)

Sep 7, 2026API request failedReasoning setting: high

Prompt and test conditions

Generate an SVG of a pelican riding a bicycle

Token limit including reasoning: 8,192 tokens

Task origin (Simon Willison)

How to read this comparison

Winning one benchmark is not an overall verdict

Your workload, budget, and required context length matter most. A coding benchmark says little about visual understanding or agent performance.

The standard price table uses direct developer rates. The provider comparison labels OpenRouter endpoints, regions, and special tariffs separately.

Every result links to its measurement source and retrieval date. Labels distinguish vendor reports, official benchmark leaderboards, and independent evaluations. Disputed or archived results are excluded.

More matchups

Compare Claude Opus 4.8 and Kimi K3 with other leading models using the same data and benchmark logic.

View the complete LLM comparison

Claude Opus 4.8 vs. Kimi K3

Change model selection

General specifications

API pricing compared

Benchmark index compared

Shared benchmarks

Capability profile from matched benchmarks

Our tests

SVG short test

Claude Opus 4.8

Kimi K3

Pelican on a bicycle

Winning one benchmark is not an overall verdict

Related LLM comparisons