llmboard.aiAI model intelligence
Home

Model Rankings

OverallOpen ModelsAgentCodingReasoningMathKnowledgeInstruction FollowingTextVision
Image GenerationImage Editing
Video GenerationImage to VideoVideo Editing
Text to SpeechSpeech to Text
Embeddings

Efficiency

Chat Token PricingImage PricingVideo PricingAudio Pricing
Chat Speed & LatencyProvider Reliability

Benchmarks

GPQAMMLU-ProAIME 2025SWE-Bench VerifiedMMLUHumanity's Last ExamLiveCodeBenchMATHHumanEvalMMMU-Pro
All Benchmarks

Tools

Model Directory

Scoring & Data

Scoring & Data
1450 models809 benchmarks

Leaderboard Center

Overall RankingCodingCore BenchmarksPrice & ValueRuntime Performance

Modalities

All ModelsImage GenerationImage EditingVideo GenerationImage-to-VideoVideo EditingText-to-SpeechSpeech-to-TextEmbeddings

Data & Methods

Scoring MethodAll Benchmarks
llmboard.aiCopyright 2026 llmboard.ai

Anthropic model product

Claude Opus 4.6

6 is an Anthropic large language model with a 1M token context window in beta and 128K output tokens.

Updated Nov 18, 2026. Default version: Claude Opus 4.6

LLMBoard Score75.9Claude Opus 4.6
Coverage80%26 benchmark families
Context window1MTokens
Official input price$5Anthropic API

On this page

  • Capability
  • Benchmarks
  • Arena
  • Pricing
  • Runtime
  • Specification
  • Versions
  • Similar models
  • About
  • FAQ

Claude Opus 4.6 Capability Profile

This profile uses the model's current scored version. Arena ratings and prices are shown separately.

Claude Opus 4.6 LLMBoard score breakdown

Claude Opus 4.6 Benchmark Results

Benchmark scores for Claude Opus 4.6.

30 of 44 rows
Columns

Show columns

Sort by
Benchmark
Score
Rank
Participants
Percentile
Evidence
Evaluated
BenchmarkGraphwalks parents >128kScore95.40%Rank01Participants7Percentile100.00%EvidenceCEvaluatedNov 17, 2026
BenchmarkOpenRCAScore34.90%Rank01Participants1Percentile100.00%EvidenceCEvaluatedNov 17, 2026
BenchmarkTau2 RetailScore91.90%Rank01Participants28Percentile100.00%EvidenceCEvaluatedNov 17, 2026
BenchmarkTau2 TelecomScore99.30%Rank01Participants37Percentile100.00%EvidenceCEvaluatedNov 17, 2026
BenchmarkFigQAScore78.30%Rank02Participants3Percentile50.00%EvidenceCEvaluatedNov 17, 2026
BenchmarkFinance AgentScore60.70%Rank03Participants8Percentile71.43%EvidenceCEvaluatedNov 17, 2026
BenchmarkOSWorldScore72.70%Rank03Participants21Percentile90.00%EvidenceCEvaluatedNov 17, 2026
BenchmarkVending-Bench 2Score8,017.59 usdRank03Participants6Percentile60.00%EvidenceCEvaluatedNov 17, 2026
BenchmarkLM Arena DocumentScore1,507.61 ratingRank03Participants39Percentile94.74%EvidenceAEvaluatedNov 9, 2026
BenchmarkLM Arena Document Style ControlScore1,496.89 ratingRank03Participants39Percentile94.74%EvidenceAEvaluatedNov 9, 2026
BenchmarkLM Arena SearchScore1,251.67 ratingRank03Participants33Percentile93.75%EvidenceAEvaluatedNov 9, 2026
BenchmarkDeepSearchQAScore91.30%Rank04Participants13Percentile75.00%EvidenceCEvaluatedNov 17, 2026
BenchmarkLM Arena Vision Style ControlScore1,298.76 ratingRank04Participants113Percentile97.32%EvidenceAEvaluatedNov 9, 2026
BenchmarkLM Arena Search FactualityScore1,227.37 ratingRank05Participants33Percentile87.50%EvidenceAEvaluatedNov 9, 2026
BenchmarkLM Arena Text Style ControlScore1,502.83 ratingRank05Participants221Percentile98.18%EvidenceAEvaluatedNov 11, 2026
BenchmarkAIME 2025Score99.79%Rank06Participants123Percentile95.90%EvidenceCEvaluatedNov 17, 2026
BenchmarkARC-AGI v2Score68.80%Rank06Participants19Percentile72.22%EvidenceCEvaluatedNov 17, 2026
BenchmarkMMMLUScore91.10%Rank06Participants51Percentile90.00%EvidenceCEvaluatedNov 17, 2026
BenchmarkMRCR v2 (8-needle)Score76.00%Rank06Participants25Percentile79.17%EvidenceCEvaluatedNov 17, 2026
BenchmarkLM Arena Text FactualityScore1,492.44 ratingRank06Participants134Percentile96.24%EvidenceAEvaluatedNov 11, 2026
BenchmarkLM Arena Search Style ControlScore1,221.74 ratingRank07Participants33Percentile81.25%EvidenceAEvaluatedNov 9, 2026
BenchmarkLM Arena TextScore1,501.48 ratingRank07Participants221Percentile97.27%EvidenceAEvaluatedNov 11, 2026
BenchmarkLM Arena VisionScore1,315.58 ratingRank07Participants113Percentile94.64%EvidenceAEvaluatedNov 9, 2026
BenchmarkGraphwalks BFS >128kScore61.50%Rank08Participants13Percentile41.67%EvidenceCEvaluatedNov 17, 2026
BenchmarkLegal Agent BenchmarkScore4.20%Rank09Participants16Percentile46.67%EvidenceBEvaluatedNov 17, 2026
BenchmarkFrontierSWEScore56.00%Rank10Participants17Percentile43.75%EvidenceBEvaluatedNov 17, 2026
BenchmarkSWE-Bench VerifiedScore80.80%Rank10Participants124Percentile92.68%EvidenceCEvaluatedNov 17, 2026
BenchmarkLiveBenchScore76.33%Rank11Participants38Percentile72.97%EvidenceBEvaluatedNov 17, 2026
BenchmarkSWE-bench MultilingualScore77.83%Rank14Participants52Percentile74.51%EvidenceCEvaluatedNov 17, 2026
BenchmarkTerminal-Bench 2.0Score65.40%Rank17Participants53Percentile69.23%EvidenceCEvaluatedNov 17, 2026

Claude Opus 4.6 Arena Results

Preference and agent-evaluation results for the default version.

30 of 100 rows
Columns

Show columns

Sort by
Arena
Category
Rank
Rating / score
Votes
Observations
Result date
Arenatext factualityCategoryfrenchRank01Rating / score1,530.77Votes2,200ObservationsN/AResult dateNov 11, 2026
Arenatext factualityCategoryspanishRank01Rating / score1,499.85Votes2,314ObservationsN/AResult dateNov 11, 2026
Arenatext factualityCategorymulti turnRank02Rating / score1,507.22Votes11,789ObservationsN/AResult dateNov 11, 2026
Arenatext style controlCategoryindustry life and physical and social scienceRank02Rating / score1,526.75Votes13,959ObservationsN/AResult dateNov 11, 2026
ArenavisionCategoryenglishRank02Rating / score1,324.18Votes9,173ObservationsN/AResult dateNov 9, 2026
ArenadocumentCategoryoverallRank03Rating / score1,507.61Votes29,456ObservationsN/AResult dateNov 9, 2026
Arenadocument style controlCategoryoverallRank03Rating / score1,496.89Votes29,456ObservationsN/AResult dateNov 9, 2026
ArenasearchCategoryoverallRank03Rating / score1,251.67Votes166,732ObservationsN/AResult dateNov 9, 2026
ArenatextCategorymulti turnRank03Rating / score1,512.05Votes14,330ObservationsN/AResult dateNov 11, 2026
Arenatext factualityCategorycodingRank03Rating / score1,550.67Votes19,519ObservationsN/AResult dateNov 11, 2026
Arenatext factualityCategoryexpertRank03Rating / score1,541.23Votes6,144ObservationsN/AResult dateNov 11, 2026
Arenatext factualityCategorygermanRank03Rating / score1,471.25Votes738ObservationsN/AResult dateNov 11, 2026
Arenatext factualityCategoryindustry mathematicalRank03Rating / score1,505.35Votes3,401ObservationsN/AResult dateNov 11, 2026
Arenatext factualityCategorypolishRank03Rating / score1,482.26Votes1,018ObservationsN/AResult dateNov 11, 2026
Arenatext style controlCategoryhard prompts englishRank03Rating / score1,534.99Votes23,908ObservationsN/AResult dateNov 11, 2026
Arenatext style controlCategoryspanishRank03Rating / score1,495.78Votes2,978ObservationsN/AResult dateNov 11, 2026
ArenavisionCategorycreative writing visionRank03Rating / score1,332.52Votes1,398ObservationsN/AResult dateNov 9, 2026
Arenavision style controlCategorycreative writing visionRank03Rating / score1,309.60Votes1,398ObservationsN/AResult dateNov 9, 2026
Arenavision style controlCategoryenglishRank03Rating / score1,301.51Votes9,173ObservationsN/AResult dateNov 9, 2026
ArenatextCategorycodingRank04Rating / score1,533.96Votes24,530ObservationsN/AResult dateNov 11, 2026
ArenatextCategoryenglishRank04Rating / score1,511.63Votes36,797ObservationsN/AResult dateNov 11, 2026
ArenatextCategoryfrenchRank04Rating / score1,511.99Votes2,779ObservationsN/AResult dateNov 11, 2026
ArenatextCategoryhard prompts englishRank04Rating / score1,530.37Votes23,908ObservationsN/AResult dateNov 11, 2026
ArenatextCategoryindustry business and management and financial operationsRank04Rating / score1,496.96Votes16,471ObservationsN/AResult dateNov 11, 2026
ArenatextCategoryinstruction followingRank04Rating / score1,520.98Votes27,202ObservationsN/AResult dateNov 11, 2026
Arenatext factualityCategorychineseRank04Rating / score1,545.23Votes4,507ObservationsN/AResult dateNov 11, 2026
Arenatext factualityCategoryenglishRank04Rating / score1,504.08Votes36,119ObservationsN/AResult dateNov 11, 2026
Arenatext factualityCategoryhard prompts englishRank04Rating / score1,533.78Votes21,750ObservationsN/AResult dateNov 11, 2026
Arenatext factualityCategoryindustry business and management and financial operationsRank04Rating / score1,499.42Votes13,718ObservationsN/AResult dateNov 11, 2026
Arenatext factualityCategoryindustry software and it servicesRank04Rating / score1,532.93Votes33,241ObservationsN/AResult dateNov 11, 2026

Claude Opus 4.6 Pricing

Official vendor API pricing appears first, followed by individual provider offers.

Official API
$5 input, $25 output per 1M
Official provider
Anthropic
Lowest third-party
From $3.25 input, $16.25 output per 1M via KoRouter
Tracked offerings
43
30 of 42 rows
Columns

Show columns

Sort by
Provider
Provider model ID
Region
Input / 1M
Output / 1M
Context
Updated
ProviderKoRouterProvider model IDclaude-opus-4-6RegionglobalInput / 1M$3.25Output / 1M$16.25Context1MUpdatedNov 18, 2026
ProviderKunavoProvider model IDclaude-opus-4-6RegionglobalInput / 1M$3.5Output / 1M$17.5Context1MUpdatedNov 18, 2026
ProviderPoeProvider model IDanthropic/claude-opus-4.6RegionglobalInput / 1M$4.29Output / 1M$21.46Context983KUpdatedNov 18, 2026
ProviderOrcaRouterProvider model IDanthropic/claude-opus-4.6RegionglobalInput / 1M$5Output / 1M$25Context1MUpdatedNov 18, 2026
ProviderVertexProvider model IDclaude-opus-4-6@defaultRegionglobalInput / 1M$5Output / 1M$25Context1MUpdatedNov 18, 2026
ProviderImpossiblProvider model IDanthropic/claude-opus-4-6RegionglobalInput / 1M$5Output / 1M$25Context1MUpdatedNov 18, 2026
ProviderJiekou.AIProvider model IDclaude-opus-4-6RegionglobalInput / 1M$5Output / 1M$25Context1MUpdatedNov 18, 2026
ProviderOpenRouterProvider model IDanthropic/claude-opus-4.6RegionglobalInput / 1M$5Output / 1M$25Context1MUpdatedNov 18, 2026
ProviderVertex (Anthropic)Provider model IDclaude-opus-4-6@defaultRegionglobalInput / 1M$5Output / 1M$25Context1MUpdatedNov 18, 2026
ProviderAurikoProvider model IDclaude-opus-4-6RegionglobalInput / 1M$5Output / 1M$25Context1MUpdatedNov 18, 2026
ProviderSnowflake CortexProvider model IDclaude-opus-4-6RegionglobalInput / 1M$5Output / 1M$25Context1MUpdatedNov 18, 2026
ProviderAnthropicProvider model IDclaude-opus-4-6RegionglobalInput / 1M$5Output / 1M$25Context1MUpdatedNov 18, 2026
ProviderDatabricksProvider model IDdatabricks-claude-opus-4-6RegionglobalInput / 1M$5Output / 1M$25Context1MUpdatedNov 18, 2026
ProviderLLM GatewayProvider model IDanthropic/claude-opus-4-6RegionglobalInput / 1M$5Output / 1M$25Context1MUpdatedNov 18, 2026
ProviderNEAR AI CloudProvider model IDanthropic/claude-opus-4-6RegionglobalInput / 1M$5Output / 1M$25Context200KUpdatedNov 18, 2026
ProviderMerge GatewayProvider model IDanthropic/claude-opus-4-6RegionglobalInput / 1M$5Output / 1M$25Context1MUpdatedNov 18, 2026
ProviderCloudflare AI GatewayProvider model IDanthropic/claude-opus-4.6RegionglobalInput / 1M$5Output / 1M$25Context1MUpdatedNov 18, 2026
ProviderZenMuxProvider model IDanthropic/claude-opus-4.6RegionglobalInput / 1M$5Output / 1M$25Context1MUpdatedNov 18, 2026
ProviderPerplexity AgentProvider model IDanthropic/claude-opus-4-6RegionglobalInput / 1M$5Output / 1M$25Context200KUpdatedNov 18, 2026
ProviderGMI CloudProvider model IDanthropic/claude-opus-4.6RegionglobalInput / 1M$5Output / 1M$25Context409.6KUpdatedNov 18, 2026
ProviderFreeModelProvider model IDclaude-opus-4-6RegionglobalInput / 1M$5Output / 1M$25Context1MUpdatedNov 18, 2026
ProviderOfoxProvider model IDanthropic/claude-opus-4.6RegionglobalInput / 1M$5Output / 1M$25Context1MUpdatedNov 18, 2026
ProviderNeonProvider model IDclaude-opus-4-6RegionglobalInput / 1M$5Output / 1M$25Context1MUpdatedNov 18, 2026
ProviderAzure Cognitive ServicesProvider model IDclaude-opus-4-6RegionglobalInput / 1M$5Output / 1M$25Context1MUpdatedNov 18, 2026
ProviderOpenCodeProvider model IDclaude-opus-4-6RegionglobalInput / 1M$5Output / 1M$25Context1MUpdatedNov 18, 2026
ProviderRequestyProvider model IDclaude-opus-4-6RegionglobalInput / 1M$5Output / 1M$25Context1MUpdatedNov 18, 2026
ProviderAzureProvider model IDclaude-opus-4-6RegionglobalInput / 1M$5Output / 1M$25Context1MUpdatedNov 18, 2026
ProviderFrogBotProvider model IDclaude-opus-4-6RegionglobalInput / 1M$5Output / 1M$25Context200KUpdatedNov 18, 2026
ProviderAIHubMixProvider model IDclaude-opus-4-6RegionglobalInput / 1M$5Output / 1M$25Context1MUpdatedNov 18, 2026
ProviderVercel AI GatewayProvider model IDanthropic/claude-opus-4.6RegionglobalInput / 1M$5Output / 1M$25Context1MUpdatedNov 18, 2026

Claude Opus 4.6 Runtime Performance

Provider-specific output speed and catalog latency for Claude Opus 4.6. Runtime does not affect the capability score.

1 row
Columns

Show columns

Sort by
Provider
Output Speed
Catalog Latency
Max Input
Max Output
Updated
ProviderAnthropicOutput Speed42.00 tok/sCatalog Latency0.50 sMax Input1MMax Output128KUpdatedNov 18, 2026

Output Speed is generated output tokens received per second. Catalog latency is reported separately from observed provider TTFT.

Claude Opus 4.6 Specifications

Technical details for the model's default version.

Version
Claude Opus 4.6
Released
Feb 5, 2026
Knowledge cutoff
Unknown
Parameters
N/A
Context window
1M
Max output
128K
Inputs
image, text
Outputs
text
Open weights
No
License
Proprietary

Claude Opus 4.6 Versions

Available versions of this model. The score column identifies the version used in the overall ranking.

1 row
Columns

Show columns

Sort by
Version
Released
LLMBoard
Parameters
Context
Max output
Open weights
License
VersionClaude Opus 4.6ReleasedFeb 5, 2026LLMBoard75.93ParametersN/AContext1MMax output128KOpen weightsNoLicenseProprietary

Models similar to Claude Opus 4.6

Recommendations prioritize the same model type and family, then the closest LLMBoard score.

#44-0.07
AN

Claude Sonnet 5

Anthropic

75.86 LLMBoard

Details
#45-0.15
AN

Claude Haiku 5.5

Anthropic

75.78 LLMBoard

Details
#29+3.93
AN

Claude Opus 4.7

Anthropic

79.86 LLMBoard

Details
#24+5.01
AN

Claude Opus 4.8

Anthropic

80.94 LLMBoard

Details
#69-5.67
AN

Claude Mythos 5.1

Anthropic

70.26 LLMBoard

Details
#74-6.30
AN

Claude Sonnet 4.6

Anthropic

69.63 LLMBoard

Details

What is Claude Opus 4.6?

Key information about Claude Opus 4.6 and its available data.

6 is an LLM from Anthropic with adaptive thinking, configurable low, medium, high, and max effort controls, and context compaction for long-running tasks. It is priced at $5 per million input tokens and $25 per million output tokens.

Data as of 2026-11-17.

FAQ

Common questions about Claude Opus 4.6.

When was Claude Opus 4.6 released?

Claude Opus 4.6's default version was released on Feb 5, 2026.

How much does Claude Opus 4.6 cost?

Claude Opus 4.6's official API price is $5 per million input tokens and $25 per million output tokens via Anthropic. The lowest tracked third-party offer starts at $3.25 input and $16.25 output via KoRouter.

Who created Claude Opus 4.6?

Claude Opus 4.6 was created by Anthropic.

What is the context window for Claude Opus 4.6?

The default version has a 1M token context window.

Is Claude Opus 4.6 open weight?

No. The default version is not marked as having publicly available weights.

How many API providers offer Claude Opus 4.6?

Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.

43 provider offerings are linked to the default version.