Head-to-head comparison

Claude Sonnet 4.6 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: 174
distinct benchmark metrics: 21
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 Sonnet 4.6 and Kimi K3
Attribute	Claude Sonnet 4.6	Kimi K3
Provider	Anthropic	Moonshot AI
Released	Feb 2026	Jul 16, 2026
Availability	Active	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	August 2025	Not published
Technical sources	Model, Context	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 Sonnet 4.6 and Kimi K3
Price type	Claude Sonnet 4.6	Kimi K3
API input	$3	$3
API output	$15	$15
Cache read	$0.3	$0.3
Cache write (5 min.)	$3.75	Not listed
Cache write (1 hr.)	$6	Not listed
Price verified	09/22/2026 Source	09/22/2026 Source

Claude Sonnet 4.6Kimi K3

API inputUSD per 1M tokens, base tier

Claude Sonnet 4.6$3

Kimi K3$3

API outputUSD per 1M tokens, base tier

Claude Sonnet 4.6$15

Kimi K3$15

Cache readUSD per 1M tokens, base tier

Claude Sonnet 4.6$0.3

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.

Provider pricing for Claude Sonnet 4.6 and Kimi K3
Model	Provider	Purchase route and tariff	Input per 1M tokens	Output per 1M tokens	Source
Claude Sonnet 4.6	Anthropic	Direct from developerStandard API	Lowest listed price: $3	Lowest listed price: $15	Source09/22/2026
	Amazon Bedrock	Via OpenRouteramazon-bedrock/eu-west-1	$3.3	$16.5	Source10/26/2026
	Amazon Bedrock	Via OpenRouteramazon-bedrock/global	Lowest listed price: $3	Lowest listed price: $15	Source10/26/2026
	Amazon Bedrock	Via OpenRouteramazon-bedrock/us	$3.3	$16.5	Source10/26/2026
	Anthropic	Via OpenRouteranthropic	Lowest listed price: $3	Lowest listed price: $15	Source10/26/2026
	Azure	Via OpenRouterazure/global	Lowest listed price: $3	Lowest listed price: $15	Source10/26/2026
	Claude Platform on AWS	Via OpenRouterclaude-on-aws	Lowest listed price: $3	Lowest listed price: $15	Source10/26/2026
	Google	Via OpenRoutergoogle-vertex/europe	$3.3	$16.5	Source10/26/2026
	Google	Via OpenRoutergoogle-vertex/global	Lowest listed price: $3	Lowest listed price: $15	Source10/26/2026
	Google	Via OpenRoutergoogle-vertex/us-east5	$3.3	$16.5	Source10/26/2026
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 Sonnet 4.6

Overall index

22.0

Kimi K3

Overall index

62.0

Kimi K3 leads in 10 of 10 shared areas.

Area	Claude Sonnet 4.6	Kimi K3
Coding	17.5	52.2
Reasoning	22.8	64.0
Knowledge	25.0	49.3
Agents	14.3	61.7
Finance	44.6	70.3
Legal	28.0	73.4
Health	13.7	68.9
Multimodal	20.4	56.3
Productivity	29.8	69.6
Education	27.4	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 Sonnet 4.6Kimi K3

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

Claude Sonnet 4.639.892 %

Kimi K316.099 %

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

Claude Sonnet 4.665.307 %

Kimi K371.562 %

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

Claude Sonnet 4.660.154 %

Kimi K366.677 %

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

Claude Sonnet 4.651.035 %

Kimi K353.114 %

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

Claude Sonnet 4.685.606 %

Kimi K392.929 %

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

Claude Sonnet 4.65 %

Kimi K312.917 %

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

Claude Sonnet 4.638.462 %

Kimi K346.154 %

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

Claude Sonnet 4.682.12 %

Kimi K386.212 %

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

Claude Sonnet 4.682.091 %

Kimi K387.185 %

MMLU-ProOverall. Higher is better. Test setup not documented as identical

Claude Sonnet 4.687.341 %

Kimi K387.973 %

MMMU-ProOverall. Higher is better. Test setup not documented as identical

Claude Sonnet 4.683.584 %

Kimi K388.15 %

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

Claude Sonnet 4.667.726 %

Kimi K366.336 %

Key to the marks:better valuebetter, but not conclusivetie

Benchmark scores for Claude Sonnet 4.6 and Kimi K3
Benchmark and task	Claude Sonnet 4.6	Kimi K3	Source
Code MigrationOverall Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Sonnet 4.6: 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 value39.892 %	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 Sonnet 4.6: Compute: max, Temperature: 1, Output limit: 128,000 tokens Kimi K3: Temperature: 1, Output limit: 262,144 tokens	65.307 %	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 Sonnet 4.6: Compute: max, Temperature: 1, Output limit: 128,000 tokens Kimi K3: Reasoning: max, Temperature: 1, Top P: 0.95, Output limit: 262,144 tokens	60.154 %	Higher measured value66.677 %	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 Sonnet 4.6: Compute: max, Temperature: 1, Output limit: 128,000 tokens Kimi K3: Reasoning: max, Temperature: 1, Top P: 0.95, Output limit: 262,144 tokens	51.035 %	Higher measured value53.114 %	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 Sonnet 4.6: Compute: max, Temperature: 1, Output limit: 128,000 tokens Kimi K3: Temperature: 1, Output limit: 262,144 tokens	85.606 %	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 Sonnet 4.6: Compute: max, Temperature: 1, Output limit: 128,000 tokens Kimi K3: Reasoning: max, Temperature: 1, Top P: 0.95, Output limit: 262,144 tokens	5 %	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 Sonnet 4.6: Compute: max, Temperature: 1, Output limit: 128,000 tokens Kimi K3: Reasoning: max, Temperature: 1, Top P: 0.95, Output limit: 262,144 tokens	38.462 %	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 Sonnet 4.6: Compute: max, Temperature: 1, Output limit: 128,000 tokens Kimi K3: Reasoning: max, Temperature: 1, Top P: 0.95, Output limit: 262,144 tokens	82.12 %	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 Sonnet 4.6: Compute: max, Temperature: 1, Output limit: 128,000 tokens Kimi K3: Reasoning: max, Output limit: 262,144 tokens	82.091 %	Higher measured value87.185 %	Vals AI Source details Data as of: 09/01/2026
MMLU-ProOverall Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Sonnet 4.6: Compute: max, Temperature: 1, Output limit: 128,000 tokens Kimi K3: Reasoning: max, Output limit: 262,144 tokens	87.341 %	Higher measured value87.973 %	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 Sonnet 4.6: Compute: max, Temperature: 1, Output limit: 128,000 tokens Kimi K3: Temperature: 1, Output limit: 262,144 tokens	83.584 %	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 Sonnet 4.6: Compute: max, Temperature: 1, Output limit: 128,000 tokens Kimi K3: Temperature: 1, Output limit: 262,144 tokens	Higher measured value67.726 %	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 Sonnet 4.6: Compute: max, Temperature: 1, Output limit: 128,000 tokens Kimi K3: Temperature: 1, Output limit: 262,144 tokens	0.5 %	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 Sonnet 4.6: Compute: max, Temperature: 1, Output limit: 128,000 tokens Kimi K3: Reasoning: max, Temperature: 1, Top P: 0.95, Output limit: 262,144 tokens	62.449 %	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 Sonnet 4.6: Compute: max, Temperature: 1, Output limit: 30,000 tokens Kimi K3: Reasoning: max, Temperature: 1, Top P: 0.95, Output limit: 262,144 tokens	46.582 %	Higher measured value52.783 %	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 Sonnet 4.6: Compute: max, Temperature: 1, Output limit: 128,000 tokens Kimi K3: Temperature: 1, Output limit: 262,144 tokens	77.4 %	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 Sonnet 4.6: Compute: max, Temperature: 1, Output limit: 128,000 tokens Kimi K3: Reasoning: max, Temperature: 1, Top P: 0.95, Output limit: 262,144 tokens	25.84 %	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 Sonnet 4.6: Compute: max, Temperature: 1, Output limit: 128,000 tokens Kimi K3: Temperature: 1, Output limit: 262,144 tokens	Higher measured value77.106 %	75.716 %	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 Sonnet 4.6: Compute: max, Temperature: 1, Output limit: 128,000 tokens Kimi K3: Temperature: 1, Output limit: 262,144 tokens	57.303 %	Higher measured value80.899 %	Vals AI Source details Data as of: 09/28/2026
Vals Multimodal IndexOverall Test details Test setup not documented as identicalNo direct winnerVersion: 1.2Metric: weighted index scoreScoring: Higher is betterClaude Sonnet 4.6: Compute: max, Temperature: 1, Output limit: 128,000 tokens Kimi K3: Temperature: 1, Output limit: 262,144 tokens	60.571 %	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 Sonnet 4.6: 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	51.476 %	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 Sonnet 4.6: 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 value30.333 %	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 Sonnet 4.6: Compute: max, Temperature: 1, Output limit: 128,000 tokens Kimi K3: Temperature: 1, Output limit: 262,144 tokens	63.17 %	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 Sonnet 4.6: Compute: max, Temperature: 1, Output limit: 128,000 tokens Kimi K3: Reasoning: max, Temperature: 1, Top P: 0.95, Output limit: 262,144 tokens	61.52 %	Higher measured value70.837 %	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 Sonnet 4.6: 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 value48.92 %	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 Sonnet 4.6: Compute: max, Temperature: 1, Output limit: 128,000 tokens Kimi K3: Temperature: 1, Output limit: 262,144 tokens	85.859 %	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 Sonnet 4.6: 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 Sonnet 4.6: 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 Sonnet 4.6: Compute: max, Temperature: 1, Output limit: 128,000 tokens Kimi K3: Reasoning: max, Temperature: 1, Top P: 0.95, Output limit: 262,144 tokens	87.991 %	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 Sonnet 4.6: Compute: max, Temperature: 1, Output limit: 128,000 tokens Kimi K3: Reasoning: max, Output limit: 262,144 tokens	No direct winner98.758 %	No direct winner98.758 %	Vals AI Source details Data as of: 09/01/2026
MMLU-ProBiology Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Sonnet 4.6: Compute: max, Temperature: 1, Output limit: 128,000 tokens Kimi K3: Reasoning: max, Output limit: 262,144 tokens	92.748 %	Higher measured value93.863 %	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 Sonnet 4.6: Compute: max, Temperature: 1, Output limit: 128,000 tokens Kimi K3: Temperature: 1, Output limit: 262,144 tokens	74.96 %	Higher measured value78.855 %	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 Sonnet 4.6: Compute: max, Temperature: 1, Output limit: 128,000 tokens Kimi K3: Temperature: 1, Output limit: 262,144 tokens	2 %	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 Sonnet 4.6: Compute: max, Temperature: 1, Output limit: 30,000 tokens Kimi K3: Reasoning: max, Temperature: 1, Top P: 0.95, Output limit: 262,144 tokens	35.318 %	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 Sonnet 4.6: Compute: max, Temperature: 1, Output limit: 128,000 tokens Kimi K3: Temperature: 1, Output limit: 262,144 tokens	87.113 %	Higher measured value92.268 %	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 Sonnet 4.6: Compute: max, Temperature: 1, Output limit: 128,000 tokens Kimi K3: Reasoning: max, Temperature: 1, Top P: 0.95, Output limit: 262,144 tokens	10 %	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 Sonnet 4.6: Compute: max, Temperature: 1, Output limit: 128,000 tokens Kimi K3: Temperature: 1, Output limit: 262,144 tokens	Higher measured value65.822 %	65.331 %	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 Sonnet 4.6: 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
Vals Multimodal IndexCorpFin v2 Test details Test setup not documented as identicalNo direct winnerVersion: 1.2Metric: benchmark scoreScoring: Higher is betterClaude Sonnet 4.6: Compute: max, Temperature: 1, Output limit: 128,000 tokens Kimi K3: Temperature: 1, Output limit: 262,144 tokens	66.667 %	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 Sonnet 4.6: 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 Sonnet 4.6: Compute: max, Temperature: 1, Output limit: 128,000 tokens Kimi K3: Temperature: 1, Output limit: 262,144 tokens	66.084 %	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 Sonnet 4.6: Compute: max, Temperature: 1, Output limit: 128,000 tokens Kimi K3: Reasoning: max, Temperature: 1, Top P: 0.95, Output limit: 262,144 tokens	78.493 %	Higher measured value82.661 %	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 Sonnet 4.6: Compute: max, Temperature: 1, Output limit: 128,000 tokens Kimi K3: Reasoning: max, Temperature: 1, Top P: 0.95, Output limit: 262,144 tokens	38.795 %	Higher measured value41.837 %	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 Sonnet 4.6: Compute: max, Temperature: 1, Output limit: 128,000 tokens Kimi K3: Temperature: 1, Output limit: 262,144 tokens	85.354 %	Higher measured value92.424 %	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 Sonnet 4.6: 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 Sonnet 4.6: Compute: max, Temperature: 1, Output limit: 128,000 tokens Kimi K3: Reasoning: max, Temperature: 1, Top P: 0.95, Output limit: 262,144 tokens	86.797 %	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 Sonnet 4.6: Compute: max, Temperature: 1, Output limit: 128,000 tokens Kimi K3: Reasoning: max, Temperature: 1, Top P: 0.95, Output limit: 262,144 tokens	82.469 %	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 Sonnet 4.6: Compute: max, Temperature: 1, Output limit: 128,000 tokens Kimi K3: Reasoning: max, Output limit: 262,144 tokens	60.571 %	Higher measured value74.286 %	Vals AI Source details Data as of: 09/01/2026
MMLU-ProBusiness Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Sonnet 4.6: Compute: max, Temperature: 1, Output limit: 128,000 tokens Kimi K3: Reasoning: max, Output limit: 262,144 tokens	91.888 %	Higher measured value92.015 %	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 Sonnet 4.6: Compute: max, Temperature: 1, Output limit: 128,000 tokens Kimi K3: Temperature: 1, Output limit: 262,144 tokens	Higher measured value60.493 %	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 Sonnet 4.6: Compute: max, Temperature: 1, Output limit: 128,000 tokens Kimi K3: Temperature: 1, Output limit: 262,144 tokens	0.5 %	Higher measured value2 %	Vals AI Source details Data as of: 10/12/2026
SAGECalculus Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Sonnet 4.6: Temperature: 1, Output limit: 30,000 tokens Kimi K3: Reasoning: max, Temperature: 1, Top P: 0.95, Output limit: 262,144 tokens	60.494 %	Higher measured value79.938 %	Vals AI Source details Data as of: 10/08/2026
SWE-bench Verified>4 hours Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Sonnet 4.6: Compute: max, Temperature: 1, Output limit: 128,000 tokens Kimi K3: Temperature: 1, Output limit: 262,144 tokens	33.333 %	Higher measured value66.667 %	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 Sonnet 4.6: Compute: max, Temperature: 1, Output limit: 128,000 tokens Kimi K3: Reasoning: max, Temperature: 1, Top P: 0.95, Output limit: 262,144 tokens	57.949 %	Higher measured value68.8 %	Vals AI Source details Data as of: 10/12/2026
TaxEval v2Stepwise Reasoning Test details Test setup not documented as identicalNo direct winnerVersion: 2Metric: accuracyScoring: Higher is betterClaude Sonnet 4.6: Compute: max, Temperature: 1, Output limit: 128,000 tokens Kimi K3: Temperature: 1, Output limit: 262,144 tokens	Higher measured value88.389 %	86.1 %	Vals AI Source details Data as of: 09/01/2026
Terminal-Bench 2.1Hard Test details Test setup not documented as identicalNo direct winnerVersion: 2.1Metric: accuracyScoring: Higher is betterClaude Sonnet 4.6: Compute: max, Temperature: 1, Output limit: 128,000 tokens Kimi K3: Temperature: 1, Output limit: 262,144 tokens	34.444 %	Higher measured value74.444 %	Vals AI Source details Data as of: 09/28/2026
Vals Multimodal IndexFinance Agent v2 Test details Test setup not documented as identicalNo direct winnerVersion: 1.2Metric: benchmark scoreScoring: Higher is betterClaude Sonnet 4.6: Compute: max, Temperature: 1, Output limit: 128,000 tokens Kimi K3: Temperature: 1, Output limit: 262,144 tokens	51.033 %	Higher measured value55.882 %	Vals AI Source details Data as of: 08/11/2026
Code MigrationCode Quality Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: mean reviewer code-quality ratingScoring: Higher is betterClaude Sonnet 4.6: 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 value3.997 / 5	3.899 / 5	Vals AI Source details Data as of: 10/12/2026
CorpFin v2Shared Max Context Test details Test setup not documented as identicalNo direct winnerVersion: 2Metric: accuracyScoring: Higher is betterClaude Sonnet 4.6: Compute: max, Temperature: 1, Output limit: 128,000 tokens Kimi K3: Temperature: 1, Output limit: 262,144 tokens	66.667 %	Higher measured value72.611 %	Vals AI Source details Data as of: 08/12/2026
EMBDCF Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Sonnet 4.6: Compute: max, Temperature: 1, Output limit: 128,000 tokens Kimi K3: Reasoning: max, Temperature: 1, Top P: 0.95, Output limit: 262,144 tokens	38.28 %	Higher measured value56.736 %	Vals AI Source details Data as of: 10/12/2026
Finance Agent (v2)Comparables Test details Test setup not documented as identicalNo direct winnerVersion: 2Metric: accuracyScoring: Higher is betterClaude Sonnet 4.6: Compute: max, Temperature: 1, Output limit: 128,000 tokens Kimi K3: Reasoning: max, Temperature: 1, Top P: 0.95, Output limit: 262,144 tokens	41.003 %	Higher measured value47.778 %	Vals AI Source details Data as of: 10/12/2026
Harvey's Legal Agent BenchmarkArbitration International Dispute Resolution · Criteria passed Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: criteria pass rateScoring: Higher is betterClaude Sonnet 4.6: Compute: max, Temperature: 1, Output limit: 128,000 tokens Kimi K3: Reasoning: max, Temperature: 1, Top P: 0.95, Output limit: 262,144 tokens	85.663 %	Higher measured value91.398 %	Vals AI Source details Data as of: 10/12/2026
Legal Research BenchBusiness & Commercial · All-pass Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: all-pass rateScoring: Higher is betterClaude Sonnet 4.6: Compute: max, Temperature: 1, Output limit: 128,000 tokens Kimi K3: Reasoning: max, Temperature: 1, Top P: 0.95, Output limit: 262,144 tokens	34.884 %	Higher measured value39.535 %	Vals AI Source details Data as of: 10/12/2026
LegalBenchIssue Tasks Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Sonnet 4.6: Compute: max, Temperature: 1, Output limit: 128,000 tokens Kimi K3: Reasoning: max, Temperature: 1, Top P: 0.95, Output limit: 262,144 tokens	86.574 %	Higher measured value90.911 %	Vals AI Source details Data as of: 10/13/2026
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 Sonnet 4.6

Kimi K3

Earlier tests

Pelican on a bicycle

A community classic for free-form SVG drawing.

Claude Sonnet 4.6

The response reached the token limit. No complete recording is available.

Reasoning (requested): high

Current attempt

Run date: Oct 6, 2026
API provider: openrouter
Requested API model: anthropic/claude-sonnet-4.6
API model reported in response: anthropic/claude-sonnet-4.6
Reasoning setting: high
Pinned endpoint: Anthropic | anthropic/claude-4.6-sonnet-20260217
Temperature: Provider default
Token limit including reasoning: 8,192 tokens
Test protocol: community-visual-tests-v1
Technical checks: Failed
Response time: 106 s

Not yet visually reviewed. A successful recording does not confirm correct physics or full compliance with the prompt.

Earlier attempts (2)

Oct 2, 2026API request failedReasoning setting: high
Oct 1, 2026API request failedReasoning setting: high

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 Sonnet 4.6 and Kimi K3 with other leading models using the same data and benchmark logic.

View the complete LLM comparison

Claude Sonnet 4.6 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 Sonnet 4.6

Kimi K3

Pelican on a bicycle

Winning one benchmark is not an overall verdict

Related LLM comparisons