Head-to-head comparison

Claude Opus 5.5 vs. Kimi K2.6

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

shared result series: 160
distinct benchmarks: 16
latest retrieval: 2026-10-15

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 5.5 and Kimi K2.6
Attribute	Claude Opus 5.5	Kimi K2.6
Provider	Anthropic	Moonshot AI
Released	Sep 22, 2026	Apr 20, 2026
Availability	Active	Active
Model type	Proprietary	Open Weights
Parameters	Not published	1T, 32B active
Architecture	Not published	Mixture of Experts
Context window	1,000,000 tokens	262,144 tokens
Knowledge cutoff	June 2026	Not published
Technical sources	Model	Model, Context

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 5.5 and Kimi K2.6
Price type	Claude Opus 5.5	Kimi K2.6
API input	$4	$0.95
API output	$20	$4
Cache read	$0.2	$0.16
Cache write (5 min.)	$5	Not listed
Cache write (1 hr.)	$8	Not listed
Price verified	09/22/2026 Source	09/22/2026 Source

Claude Opus 5.5Kimi K2.6

API inputUSD per 1M tokens, base tier

Claude Opus 5.5$4

Kimi K2.6$0.95

API outputUSD per 1M tokens, base tier

Claude Opus 5.5$20

Kimi K2.6$4

Cache readUSD per 1M tokens, base tier

Claude Opus 5.5$0.2

Kimi K2.6$0.16

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 Opus 5.5 and Kimi K2.6
Model	Provider	Purchase route and tariff	Input per 1M tokens	Output per 1M tokens	Source
Claude Opus 5.5	Anthropic	Direct from developerStandard API	Lowest listed price: $4	Lowest listed price: $20	Source09/22/2026
	Amazon Bedrock	Via OpenRouteramazon-bedrock	Lowest listed price: $4	Lowest listed price: $20	Source10/17/2026
	Amazon Bedrock	Via OpenRouteramazon-bedrock/eu-west-1	$4.4	$22	Source10/17/2026
	Amazon Bedrock	Via OpenRouteramazon-bedrock/us-east-1	$4.4	$22	Source10/17/2026
	Anthropic	Via OpenRouteranthropic	Lowest listed price: $4	Lowest listed price: $20	Source10/17/2026
	Anthropic	Via OpenRouteranthropic/fast	$8	$40	Source10/17/2026
	Azure	Via OpenRouterazure/global	Lowest listed price: $4	Lowest listed price: $20	Source10/17/2026
	Azure	Via OpenRouterazure/us	$4.4	$22	Source10/17/2026
	Claude Platform on AWS	Via OpenRouterclaude-on-aws	Lowest listed price: $4	Lowest listed price: $20	Source10/17/2026
	Google	Via OpenRoutergoogle-vertex/europe	$4.4	$22	Source10/17/2026
	Google	Via OpenRoutergoogle-vertex/global	Lowest listed price: $4	Lowest listed price: $20	Source10/17/2026
	Google	Via OpenRoutergoogle-vertex/us	$4.4	$22	Source10/17/2026
Kimi K2.6	Moonshot AI	Direct from developerStandard API	$0.95	$4	Source09/22/2026
	AtlasCloud	Via OpenRouteratlas-cloud/int4	$0.95	$4	Source10/17/2026
	Baidu	Via OpenRouterbaidu/fp4	Lowest listed price: $0.4323	Lowest listed price: $1.82	Source10/17/2026
	Chutes	Via OpenRouterchutes/int4	$0.45	$1.95	Source10/17/2026
	Cloudflare	Via OpenRoutercloudflare	$0.95	$4	Source10/17/2026
	CoreWeave	Via OpenRoutercoreweave/fp4	$0.65	$3.41	Source10/17/2026
	Crusoe	Via OpenRoutercrusoe/bf16	$0.7	$3.5	Source10/17/2026
	DeepInfra	Via OpenRouterdeepinfra/fp4	$0.75	$3.5	Source10/17/2026
	DigitalOcean	Via OpenRouterdigitalocean	$0.57	$2.4	Source10/17/2026
	GMICloud	Via OpenRoutergmicloud/fp8	$0.855	$3.6	Source10/17/2026
	Inceptron	Via OpenRouterinceptron/int4	$0.4323	$3.2	Source10/17/2026
	Moonshot AI	Via OpenRoutermoonshotai/int4	$0.95	$4	Source10/17/2026
	Novita	Via OpenRouternovita	$0.8	$3.4	Source10/17/2026
	Parasail	Via OpenRouterparasail/int4	$0.75	$3.5	Source10/17/2026
	Phala	Via OpenRouterphala	$1.09	$4.6	Source10/17/2026
	SiliconFlow	Via OpenRoutersiliconflow/fp8	$0.77	$3.4	Source10/17/2026
	StreamLake	Via OpenRouterstreamlake/fp8	$0.5985	$2.52	Source10/17/2026
	Venice	Via OpenRoutervenice/int4	$0.75	$3.5	Source10/17/2026

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

Claude Opus 5.5Kimi K2.6

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

Claude Opus 5.566.646 %

Kimi K2.627.768 %

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

Claude Opus 5.575.938 %

Kimi K2.657.855 %

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

Claude Opus 5.558.587 %

Kimi K2.644.899 %

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

Claude Opus 5.53.75 %

Kimi K2.61.667 %

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

Claude Opus 5.550.481 %

Kimi K2.615.865 %

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

Claude Opus 5.51,811.149

Kimi K2.61,509.237

LMArena Text, Style ControlOverall. Higher is better. Test setup not documented as identical

Claude Opus 5.51,508.083

Kimi K2.61,460.76

LMArena Vision, Style ControlOverall. Higher is better. Test setup not documented as identical

Claude Opus 5.51,292.688

Kimi K2.61,265.373

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

Claude Opus 5.549.797 %

Kimi K2.640.142 %

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

Claude Opus 5.591.43 %

Kimi K2.678.149 %

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

Claude Opus 5.518.5 %

Kimi K2.60 %

Public Benefits Bench v1.1Overall. Higher is better. Test setup not documented as identical

Claude Opus 5.570.636 %

Kimi K2.656.631 %

Key to the marks:better valuebetter, but not conclusivetie

Benchmark scores for Claude Opus 5.5 and Kimi K2.6
Benchmark and task	Claude Opus 5.5	Kimi K2.6	Source
Code MigrationOverall Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Opus 5.5: Compute: max, Temperature: 1, Output limit: 128,000 tokens Kimi K2.6: Top P: 0.95, Output limit: 128,000 tokens	Higher measured value66.646 %	27.768 %	Vals AI Source details Data as of: 10/12/2026
EMBOverall Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Opus 5.5: Compute: max, Temperature: 1, Output limit: 128,000 tokens Kimi K2.6: Top P: 0.95, Output limit: 128,000 tokens	Higher measured value75.938 %	57.855 %	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 5.5: Compute: max, Temperature: 1, Output limit: 128,000 tokens Kimi K2.6: Top P: 0.95, Output limit: 128,000 tokens	Higher measured value58.587 %	44.899 %	Vals AI Source details Data as of: 10/12/2026
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 5.5: Compute: max, Temperature: 1, Output limit: 128,000 tokens Kimi K2.6: Top P: 0.95, Output limit: 128,000 tokens	Higher measured value3.75 %	1.667 %	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 5.5: Compute: max, Temperature: 1, Output limit: 128,000 tokens Kimi K2.6: Top P: 0.95, Output limit: 128,000 tokens	Higher measured value50.481 %	15.865 %	Vals AI Source details Data as of: 10/12/2026
LMArena Code Arena WebDevOverall Test details Test setup not documented as identicalNo direct winnerVersion: webdevMetric: WebDev Arena Bradley-Terry ratingScoring: Higher is betterClaude Opus 5.5: Snapshot: claude-opus-5.5-max, Reasoning: max, Harness: Arena Code Arena WebDev Kimi K2.6: Snapshot: kimi-k2.6, Harness: Arena Code Arena WebDevClaude Opus 5.5: Arena rating from 2,597 published pairwise votes.Kimi K2.6: Arena rating from 10,192 published pairwise votes.	Higher measured value1,811.149 95% confidence interval: ±14.586The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.	1,509.237 95% confidence interval: ±7.227The 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
LMArena Text, Style ControlOverall Test details Test setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterClaude Opus 5.5: Snapshot: claude-opus-5.5-high, Reasoning: high, Harness: Arena Text, style control Kimi K2.6: Snapshot: kimi-k2.6, Harness: Arena Text, style controlClaude Opus 5.5: Arena rating from 7,687 published pairwise votes.Kimi K2.6: Arena rating from 40,030 published pairwise votes.	Higher measured value1,508.083 95% confidence interval: ±7.535The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.	1,460.76 95% confidence interval: ±4.428The 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
LMArena Vision, Style ControlOverall Test details Test setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterClaude Opus 5.5: Snapshot: claude-opus-5.5-high, Reasoning: high, Harness: Arena Vision, style control Kimi K2.6: Snapshot: kimi-k2.6, Harness: Arena Vision, style controlClaude Opus 5.5: Arena rating from 2,508 published pairwise votes.Kimi K2.6: Arena rating from 16,379 published pairwise votes.	Higher measured value1,292.688 95% confidence interval: ±12.73The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.	1,265.373 95% confidence interval: ±6.837The 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: 10/09/2026
MedCodeOverall Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Opus 5.5: Compute: max, Temperature: 1, Output limit: 128,000 tokens Kimi K2.6: Top P: 0.95, Output limit: 30,000 tokens	Higher measured value49.797 %	40.142 %	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 5.5: Compute: max, Temperature: 1, Output limit: 128,000 tokens Kimi K2.6: Top P: 0.95, Output limit: 30,000 tokens	Higher measured value91.43 %	78.149 %	Vals AI Source details Data as of: 10/13/2026
ProgramBenchOverall Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: fully resolved rateScoring: Higher is betterClaude Opus 5.5: Compute: max, Temperature: 1, Output limit: 128,000 tokens Kimi K2.6: Top P: 0.95, Output limit: 128,000 tokens	Higher measured value18.5 %	0 %	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 5.5: Compute: max, Temperature: 1, Output limit: 128,000 tokens Kimi K2.6: Top P: 0.95, Output limit: 128,000 tokens	Higher measured value70.636 %	56.631 %	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 5.5: Compute: max, Temperature: 1, Output limit: 30,000 tokens Kimi K2.6: Top P: 0.95, Output limit: 30,000 tokens	45.831 %	Higher measured value50.224 %	Vals AI Source details Data as of: 10/08/2026
Tax Agent BenchOverall Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Opus 5.5: Compute: max, Temperature: 1, Output limit: 128,000 tokens Kimi K2.6: Top P: 0.95, Output limit: 128,000 tokens	Higher measured value45.573 %	12.404 %	Vals AI Source details Data as of: 10/12/2026
Terminal-Bench 2.1Overall Test details Test setup not documented as identicalNo direct winnerVersion: 2.1Metric: accuracyScoring: Higher is betterClaude Opus 5.5: Compute: high, Temperature: 1, Output limit: 128,000 tokens Kimi K2.6: Top P: 0.95, Output limit: 256,000 tokens	Higher measured value87.64 %	53.558 %	Vals AI Source details Data as of: 09/28/2026
Vibe Code Bench v1.1Overall Test details Test setup not documented as identicalNo direct winnerVersion: 1.1Metric: accuracyScoring: Higher is betterClaude Opus 5.5: Compute: max, Harness: OpenHands, Temperature: 1, Output limit: 128,000 tokens Kimi K2.6: Harness: OpenHands, Top P: 0.95, Output limit: 128,000 tokens	Higher measured value90.294 %	37.891 %	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 5.5: Compute: max, Temperature: 1, Output limit: 128,000 tokens Kimi K2.6: Top P: 0.95, Output limit: 128,000 tokens	Higher measured value65.528 %	17.977 %	Vals AI Source details Data as of: 10/12/2026
EMBComps Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Opus 5.5: Compute: max, Temperature: 1, Output limit: 128,000 tokens Kimi K2.6: Top P: 0.95, Output limit: 128,000 tokens	Higher measured value76.405 %	61.395 %	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 5.5: Compute: max, Temperature: 1, Output limit: 128,000 tokens Kimi K2.6: Top P: 0.95, Output limit: 128,000 tokens	Higher measured value54.528 %	37.934 %	Vals AI Source details Data as of: 10/12/2026
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 5.5: Compute: max, Temperature: 1, Output limit: 128,000 tokens Kimi K2.6: Top P: 0.95, Output limit: 128,000 tokens	Higher measured value82.246 %	63.768 %	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 5.5: Compute: max, Temperature: 1, Output limit: 128,000 tokens Kimi K2.6: Top P: 0.95, Output limit: 128,000 tokens	Higher measured value65.152 %	18.182 %	Vals AI Source details Data as of: 10/12/2026
LMArena Code Arena WebDevImage to webdev Test details Test setup not documented as identicalNo direct winnerVersion: webdevMetric: WebDev Arena Bradley-Terry ratingScoring: Higher is betterClaude Opus 5.5: Snapshot: claude-opus-5.5-max, Reasoning: max, Harness: Arena Code Arena WebDev Kimi K2.6: Snapshot: kimi-k2.6, Harness: Arena Code Arena WebDevClaude Opus 5.5: Arena rating from 493 published pairwise votes.Kimi K2.6: Arena rating from 3,593 published pairwise votes.	Higher measured value1,748.511 95% confidence interval: ±30.162The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.	1,521.231 95% confidence interval: ±11.456The 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: 10/09/2026
LMArena Text, Style ControlBusiness, management and finance Test details Test setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterClaude Opus 5.5: Snapshot: claude-opus-5.5-high, Reasoning: high, Harness: Arena Text, style control Kimi K2.6: Snapshot: kimi-k2.6, Harness: Arena Text, style controlClaude Opus 5.5: Arena rating from 1,370 published pairwise votes.Kimi K2.6: Arena rating from 7,937 published pairwise votes.	Higher measured value1,492.054 95% confidence interval: ±16.446The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.	1,454.55 95% confidence interval: ±7.536The 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
LMArena Vision, Style ControlCreative writing vision Test details Test setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterClaude Opus 5.5: Snapshot: claude-opus-5.5-high, Reasoning: high, Harness: Arena Vision, style control Kimi K2.6: Snapshot: kimi-k2.6, Harness: Arena Vision, style controlClaude Opus 5.5: Arena rating from 219 published pairwise votes.Kimi K2.6: Arena rating from 917 published pairwise votes.	Higher measured value1,301.035 95% confidence interval: ±42.823The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.	1,253.54 95% confidence interval: ±20.065The 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: 10/09/2026
ProgramBenchAlmost Resolved Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: almost-resolved rateScoring: Higher is betterClaude Opus 5.5: Compute: max, Temperature: 1, Output limit: 128,000 tokens Kimi K2.6: Top P: 0.95, Output limit: 128,000 tokens	Higher measured value65 %	0.5 %	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 5.5: Compute: max, Temperature: 1, Output limit: 30,000 tokens Kimi K2.6: Top P: 0.95, Output limit: 30,000 tokens	32.54 %	Higher measured value42.857 %	Vals AI Source details Data as of: 10/08/2026
Tax Agent BenchControversy & Precedence Analysis Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Opus 5.5: Compute: max, Temperature: 1, Output limit: 128,000 tokens Kimi K2.6: Top P: 0.95, Output limit: 128,000 tokens	Higher measured value30 %	3.333 %	Vals AI Source details Data as of: 10/12/2026
Terminal-Bench 2.1Easy Test details Test setup not documented as identicalNo direct winnerVersion: 2.1Metric: accuracyScoring: Higher is betterClaude Opus 5.5: Compute: high, Temperature: 1, Output limit: 128,000 tokens Kimi K2.6: Top P: 0.95, Output limit: 256,000 tokens	Higher measured value100 %	83.333 %	Vals AI Source details Data as of: 09/28/2026
Code MigrationCOBOL Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Opus 5.5: Compute: max, Temperature: 1, Output limit: 128,000 tokens Kimi K2.6: Top P: 0.95, Output limit: 128,000 tokens	Higher measured value70 %	57.143 %	Vals AI Source details Data as of: 10/12/2026
EMBDataroom Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Opus 5.5: Compute: max, Temperature: 1, Output limit: 128,000 tokens Kimi K2.6: Top P: 0.95, Output limit: 128,000 tokens	Higher measured value84.873 %	75.069 %	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 5.5: Compute: max, Temperature: 1, Output limit: 128,000 tokens Kimi K2.6: Top P: 0.95, Output limit: 128,000 tokens	Higher measured value48.111 %	32.584 %	Vals AI Source details Data as of: 10/12/2026
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 5.5: Compute: max, Temperature: 1, Output limit: 128,000 tokens Kimi K2.6: Top P: 0.95, Output limit: 128,000 tokens	No direct winner0 %	No direct winner0 %	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 5.5: Compute: max, Temperature: 1, Output limit: 128,000 tokens Kimi K2.6: Top P: 0.95, Output limit: 128,000 tokens	Higher measured value85.427 %	75.531 %	Vals AI Source details Data as of: 10/12/2026
LMArena Code Arena WebDevWebdev Test details Test setup not documented as identicalNo direct winnerVersion: webdevMetric: WebDev Arena Bradley-Terry ratingScoring: Higher is betterClaude Opus 5.5: Snapshot: claude-opus-5.5-max, Reasoning: max, Harness: Arena Code Arena WebDev Kimi K2.6: Snapshot: kimi-k2.6, Harness: Arena Code Arena WebDevClaude Opus 5.5: Arena rating from 2,597 published pairwise votes.Kimi K2.6: Arena rating from 10,192 published pairwise votes.	Higher measured value1,811.149 95% confidence interval: ±14.586The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.	1,509.237 95% confidence interval: ±7.227The 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
LMArena Text, Style ControlChinese Test details Test setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterClaude Opus 5.5: Snapshot: claude-opus-5.5-high, Reasoning: high, Harness: Arena Text, style control Kimi K2.6: Snapshot: kimi-k2.6, Harness: Arena Text, style controlClaude Opus 5.5: Arena rating from 704 published pairwise votes.Kimi K2.6: Arena rating from 2,315 published pairwise votes.	Higher measured value1,574.432 95% confidence interval: ±22.751The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.	1,516.207 95% confidence interval: ±12.863The 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
LMArena Vision, Style ControlDiagram Test details Test setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterClaude Opus 5.5: Snapshot: claude-opus-5.5-high, Reasoning: high, Harness: Arena Vision, style control Kimi K2.6: Snapshot: kimi-k2.6, Harness: Arena Vision, style controlClaude Opus 5.5: Arena rating from 589 published pairwise votes.Kimi K2.6: Arena rating from 4,312 published pairwise votes.	Higher measured value1,324.12 95% confidence interval: ±25.101The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.	1,293.59 95% confidence interval: ±10.255The 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: 10/09/2026
ProgramBenchFully Resolved Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: fully resolved rateScoring: Higher is betterClaude Opus 5.5: Compute: max, Temperature: 1, Output limit: 128,000 tokens Kimi K2.6: Top P: 0.95, Output limit: 128,000 tokens	Higher measured value18.5 %	0 %	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 Opus 5.5: Compute: max, Temperature: 1, Output limit: 30,000 tokens Kimi K2.6: Top P: 0.95, Output limit: 30,000 tokens	Higher measured value83.642 %	22.839 %	Vals AI Source details Data as of: 10/08/2026
Tax Agent BenchControversy & Precedence Analysis Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Opus 5.5: Compute: max, Temperature: 1, Output limit: 128,000 tokens Kimi K2.6: Top P: 0.95, Output limit: 128,000 tokens	Higher measured value66.871 %	42.296 %	Vals AI Source details Data as of: 10/12/2026
Terminal-Bench 2.1Hard Test details Test setup not documented as identicalNo direct winnerVersion: 2.1Metric: accuracyScoring: Higher is betterClaude Opus 5.5: Compute: high, Temperature: 1, Output limit: 128,000 tokens Kimi K2.6: Top P: 0.95, Output limit: 256,000 tokens	Higher measured value81.111 %	25.556 %	Vals AI Source details Data as of: 09/28/2026
Code MigrationCode Quality Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: mean reviewer code-quality ratingScoring: Higher is betterClaude Opus 5.5: Compute: max, Temperature: 1, Output limit: 128,000 tokens Kimi K2.6: Top P: 0.95, Output limit: 128,000 tokens	Higher measured value4.541 / 5	3.149 / 5	Vals AI Source details Data as of: 10/12/2026
EMBDCF Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Opus 5.5: Compute: max, Temperature: 1, Output limit: 128,000 tokens Kimi K2.6: Top P: 0.95, Output limit: 128,000 tokens	Higher measured value70.139 %	49.675 %	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 Opus 5.5: Compute: max, Temperature: 1, Output limit: 128,000 tokens Kimi K2.6: Top P: 0.95, Output limit: 128,000 tokens	Higher measured value45.756 %	41.069 %	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 Opus 5.5: Compute: max, Temperature: 1, Output limit: 128,000 tokens Kimi K2.6: Top P: 0.95, Output limit: 128,000 tokens	Higher measured value82.969 %	50.179 %	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 Opus 5.5: Compute: max, Temperature: 1, Output limit: 128,000 tokens Kimi K2.6: Top P: 0.95, Output limit: 128,000 tokens	Higher measured value48.837 %	20.93 %	Vals AI Source details Data as of: 10/12/2026
LMArena Code Arena WebDevWebdev-html Test details Test setup not documented as identicalNo direct winnerVersion: webdevMetric: WebDev Arena Bradley-Terry ratingScoring: Higher is betterClaude Opus 5.5: Snapshot: claude-opus-5.5-max, Reasoning: max, Harness: Arena Code Arena WebDev Kimi K2.6: Snapshot: kimi-k2.6, Harness: Arena Code Arena WebDevClaude Opus 5.5: Arena rating from 122 published pairwise votes.Kimi K2.6: Arena rating from 1,160 published pairwise votes.	Higher measured value1,762.971 95% confidence interval: ±64.035The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.	1,484.407 95% confidence interval: ±18.204The 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
LMArena Text, Style ControlCoding Test details Test setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterClaude Opus 5.5: Snapshot: claude-opus-5.5-high, Reasoning: high, Harness: Arena Text, style control Kimi K2.6: Snapshot: kimi-k2.6, Harness: Arena Text, style controlClaude Opus 5.5: Arena rating from 1,755 published pairwise votes.Kimi K2.6: Arena rating from 11,100 published pairwise votes.	Higher measured value1,545.148 95% confidence interval: ±14.437The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.	1,515.795 95% confidence interval: ±6.881The 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
LMArena Vision, Style ControlEnglish Test details Test setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterClaude Opus 5.5: Snapshot: claude-opus-5.5-high, Reasoning: high, Harness: Arena Vision, style control Kimi K2.6: Snapshot: kimi-k2.6, Harness: Arena Vision, style controlClaude Opus 5.5: Arena rating from 818 published pairwise votes.Kimi K2.6: Arena rating from 6,752 published pairwise votes.	Higher measured value1,286.241 95% confidence interval: ±21.812The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.	1,268.011 95% confidence interval: ±9.51The 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: 10/09/2026
ProgramBenchRaw Pass Rate Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: raw test pass rateScoring: Higher is betterClaude Opus 5.5: Compute: max, Temperature: 1, Output limit: 128,000 tokens Kimi K2.6: Top P: 0.95, Output limit: 128,000 tokens	Higher measured value86.986 %	47.952 %	Vals AI Source details Data as of: 10/12/2026
SAGELinear Algebra Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Opus 5.5: Compute: max, Temperature: 1, Output limit: 30,000 tokens Kimi K2.6: Top P: 0.95, Output limit: 30,000 tokens	66.859 %	Higher measured value68.132 %	Vals AI Source details Data as of: 10/08/2026
Tax Agent BenchCurrent & Temporal Analysis Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Opus 5.5: Compute: max, Temperature: 1, Output limit: 128,000 tokens Kimi K2.6: Top P: 0.95, Output limit: 128,000 tokens	Higher measured value46.558 %	26.467 %	Vals AI Source details Data as of: 10/12/2026
Terminal-Bench 2.1Medium Test details Test setup not documented as identicalNo direct winnerVersion: 2.1Metric: accuracyScoring: Higher is betterClaude Opus 5.5: Compute: high, Temperature: 1, Output limit: 128,000 tokens Kimi K2.6: Top P: 0.95, Output limit: 256,000 tokens	Higher measured value90.303 %	66.667 %	Vals AI Source details Data as of: 09/28/2026
EMBLBO Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Opus 5.5: Compute: max, Temperature: 1, Output limit: 128,000 tokens Kimi K2.6: Top P: 0.95, Output limit: 128,000 tokens	Higher measured value69.013 %	43.117 %	Vals AI Source details Data as of: 10/12/2026
Finance Agent (v2)Disclosure Analysis Test details Test setup not documented as identicalNo direct winnerVersion: 2Metric: accuracyScoring: Higher is betterClaude Opus 5.5: Compute: max, Temperature: 1, Output limit: 128,000 tokens Kimi K2.6: Top P: 0.95, Output limit: 128,000 tokens	Higher measured value71.045 %	52.124 %	Vals AI Source details Data as of: 10/12/2026
Harvey's Legal Agent BenchmarkArbitration International Dispute Resolution · Task fully resolved Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: task resolution rateScoring: Higher is betterClaude Opus 5.5: Compute: max, Temperature: 1, Output limit: 128,000 tokens Kimi K2.6: Top P: 0.95, Output limit: 128,000 tokens	No direct winner0 %	No direct winner0 %	Vals AI Source details Data as of: 10/12/2026
Legal Research BenchBusiness & Commercial · Weighted partial credit Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: weighted partial-credit scoreScoring: Higher is betterClaude Opus 5.5: Compute: max, Temperature: 1, Output limit: 128,000 tokens Kimi K2.6: Top P: 0.95, Output limit: 128,000 tokens	70.961 %	Higher measured value78.436 %	Vals AI Source details Data as of: 10/12/2026
LMArena Code Arena WebDevWebdev-react Test details Test setup not documented as identicalNo direct winnerVersion: webdevMetric: WebDev Arena Bradley-Terry ratingScoring: Higher is betterClaude Opus 5.5: Snapshot: claude-opus-5.5-max, Reasoning: max, Harness: Arena Code Arena WebDev Kimi K2.6: Snapshot: kimi-k2.6, Harness: Arena Code Arena WebDevClaude Opus 5.5: Arena rating from 1,788 published pairwise votes.Kimi K2.6: Arena rating from 7,354 published pairwise votes.	Higher measured value1,859.041 95% confidence interval: ±18.379The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.	1,504.994 95% confidence interval: ±7.997The 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
LMArena Text, Style ControlCreative writing Test details Test setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterClaude Opus 5.5: Snapshot: claude-opus-5.5-high, Reasoning: high, Harness: Arena Text, style control Kimi K2.6: Snapshot: kimi-k2.6, Harness: Arena Text, style controlClaude Opus 5.5: Arena rating from 1,834 published pairwise votes.Kimi K2.6: Arena rating from 6,330 published pairwise votes.	Higher measured value1,517.113 95% confidence interval: ±15.408The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.	1,432.668 95% confidence interval: ±8.216The 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
LMArena Vision, Style ControlHomework Test details Test setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterClaude Opus 5.5: Snapshot: claude-opus-5.5-high, Reasoning: high, Harness: Arena Vision, style control Kimi K2.6: Snapshot: kimi-k2.6, Harness: Arena Vision, style controlClaude Opus 5.5: Arena rating from 322 published pairwise votes.Kimi K2.6: Arena rating from 2,273 published pairwise votes.	Higher measured value1,348.192 95% confidence interval: ±33.266The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.	1,302.204 95% confidence interval: ±13.011The 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: 10/09/2026
SAGEPartial Differential Equations Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Opus 5.5: Compute: max, Temperature: 1, Output limit: 30,000 tokens Kimi K2.6: Top P: 0.95, Output limit: 30,000 tokens	38.095 %	Higher measured value39.683 %	Vals AI Source details Data as of: 10/08/2026
Tax Agent BenchCurrent & Temporal Analysis Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Opus 5.5: Compute: max, Temperature: 1, Output limit: 128,000 tokens Kimi K2.6: Top P: 0.95, Output limit: 128,000 tokens	Higher measured value73.299 %	51.239 %	Vals AI Source details Data as of: 10/12/2026
EMBM&A Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Opus 5.5: Compute: max, Temperature: 1, Output limit: 128,000 tokens Kimi K2.6: Top P: 0.95, Output limit: 128,000 tokens	Higher measured value82.31 %	64.205 %	Vals AI Source details Data as of: 10/12/2026
Finance Agent (v2)Earnings Analysis Test details Test setup not documented as identicalNo direct winnerVersion: 2Metric: accuracyScoring: Higher is betterClaude Opus 5.5: Compute: max, Temperature: 1, Output limit: 128,000 tokens Kimi K2.6: Top P: 0.95, Output limit: 128,000 tokens	Higher measured value77.992 %	63.824 %	Vals AI Source details Data as of: 10/12/2026
Harvey's Legal Agent BenchmarkBanking Finance · Criteria passed Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: criteria pass rateScoring: Higher is betterClaude Opus 5.5: Compute: max, Temperature: 1, Output limit: 128,000 tokens Kimi K2.6: Top P: 0.95, Output limit: 128,000 tokens	Higher measured value88.848 %	84.758 %	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: 4ae5d8eeb9a9

Claude Opus 5.5

Unavailable in this round

Kimi K2.6

Earlier tests

Pelican on a bicycle

A community classic for free-form SVG drawing.

Claude Opus 5.5

Reasoning (requested): high

Current attempt

Run date: Oct 1, 2026
API provider: openrouter
Requested API model: anthropic/claude-opus-5.5
API model reported in response: anthropic/claude-opus-5.5
Reasoning setting: high
Pinned endpoint: Anthropic | anthropic/claude-opus-5.5-20260921
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: 33.2 s

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

Kimi K2.6

Output withheld for safety

Reasoning (requested): high

Current attempt

Run date: Oct 5, 2026
API provider: openrouter
Requested API model: moonshotai/kimi-k2.6
API model reported in response: moonshotai/kimi-k2.6
Reasoning setting: high
Pinned endpoint: Moonshot AI | moonshotai/kimi-k2.6-20260420
Temperature: Provider default
Token limit including reasoning: 8,192 tokens
Test protocol: community-visual-tests-v1
Technical checks: Failed
Response time: 124 s

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

Earlier attempts (3)

Oct 2, 2026Output withheld for safetyReasoning setting: high
Oct 1, 2026Output withheld for safetyReasoning setting: high
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 5.5 and Kimi K2.6 with other leading models using the same data and benchmark logic.

View the complete LLM comparison

Claude Opus 5.5 vs. Kimi K2.6

Change model selection

General specifications

API pricing compared

Shared benchmarks

Capability profile from matched benchmarks

Our tests

SVG short test

Claude Opus 5.5

Kimi K2.6

Pelican on a bicycle

Winning one benchmark is not an overall verdict

Related LLM comparisons