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 DirectoryCompare Models

Scoring & Data

Scoring & Data
393 models668 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 BenchmarksReasoningMath

Vendors

All VendorsOpenAIAnthropicGoogle
llmboard.aiCopyright 2026 llmboard.ai

Anthropic model product

Claude Opus 4

Claude Opus 4 is Anthropic's most powerful model and the world's best coding model, part of the Claude 4 family.

Updated Aug 17, 2026. Default version: Claude Opus 4

Compare
LLMBoard Score45.3Claude Opus 4
Coverage80%9 benchmark families
Context window200KTokens
Official input priceN/AOfficial price unavailable

On this page

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

Claude Opus 4 Capability Profile

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

Claude Opus 4 LLMBoard score breakdown

Claude Opus 4 Benchmark Results

Benchmark scores for Claude Opus 4.

9 rows
Columns

Show columns

Sort by
Benchmark
Score
Rank
Participants
Percentile
Evidence
Evaluated
BenchmarkMMMU (validation)Score76.5%Rank03Participants4Percentile33.3%EvidenceCEvaluatedAug 17, 2026
BenchmarkTAU-bench RetailScore81.4%Rank03Participants25Percentile91.7%EvidenceCEvaluatedAug 17, 2026
BenchmarkTAU-bench AirlineScore59.6%Rank08Participants23Percentile68.2%EvidenceCEvaluatedAug 17, 2026
BenchmarkTerminal-BenchScore39.2%Rank10Participants25Percentile62.5%EvidenceCEvaluatedAug 17, 2026
BenchmarkARC-AGI v2Score8.6%Rank15Participants17Percentile12.5%EvidenceBEvaluatedAug 17, 2026
BenchmarkMMMLUScore88.8%Rank16Participants49Percentile68.8%EvidenceCEvaluatedAug 17, 2026
BenchmarkSWE-Bench VerifiedScore72.5%Rank54Participants111Percentile51.8%EvidenceCEvaluatedAug 17, 2026
BenchmarkAIME 2025Score75.5%Rank78Participants115Percentile32.5%EvidenceCEvaluatedAug 17, 2026
BenchmarkGPQAScore79.6%Rank93Participants239Percentile61.3%EvidenceCEvaluatedAug 17, 2026

Claude Opus 4 Arena Results

Preference and agent-evaluation results for the default version.

11 rows
Columns

Show columns

Sort by
Arena
Category
Rank
Rating / score
Votes
Observations
Result date
Arenasearch style controlCategoryoverallRank25Rating / score1150.7Votes31,205ObservationsN/AResult dateJul 21, 2026
Arenasearch factualityCategoryoverallRank27Rating / score1138.1Votes14,073ObservationsN/AResult dateJul 21, 2026
ArenasearchCategoryoverallRank30Rating / score1126.4Votes31,205ObservationsN/AResult dateJul 21, 2026
Arenavision style controlCategoryoverallRank68Rating / score1206.9Votes1,299ObservationsN/AResult dateAug 6, 2026
ArenavisionCategoryoverallRank78Rating / score1191.0Votes1,299ObservationsN/AResult dateAug 6, 2026
Arenavision style controlCategoryoverallRank79Rating / score1188.9Votes2,201ObservationsN/AResult dateAug 6, 2026
ArenavisionCategoryoverallRank85Rating / score1175.6Votes2,201ObservationsN/AResult dateAug 6, 2026
Arenatext style controlCategoryoverallRank102Rating / score1424.9Votes37,015ObservationsN/AResult dateAug 12, 2026
Arenatext style controlCategoryoverallRank125Rating / score1412.5Votes44,351ObservationsN/AResult dateAug 12, 2026
ArenatextCategoryoverallRank153Rating / score1375.7Votes37,015ObservationsN/AResult dateAug 12, 2026
ArenatextCategoryoverallRank169Rating / score1364.3Votes44,351ObservationsN/AResult dateAug 12, 2026

Claude Opus 4 Pricing

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

Official API
N/A
Official provider
N/A
Lowest third-party
From $13 input, $64 output per 1M via Poe
Tracked offerings
13
13 rows
Columns

Show columns

Sort by
Provider
Provider model ID
Region
Input / 1M
Output / 1M
Context
Updated
ProviderPoeProvider model IDanthropic/claude-opus-4RegionglobalInput / 1M$13Output / 1M$64Context192.5KUpdatedAug 17, 2026
ProviderJiekou.AIProvider model IDclaude-opus-4-20250514RegionglobalInput / 1M$13.5Output / 1M$67.5Context200KUpdatedAug 17, 2026
ProviderOrcaRouterProvider model IDanthropic/claude-opus-4RegionglobalInput / 1M$15Output / 1M$75Context200KUpdatedAug 17, 2026
ProviderNanoGPTProvider model IDclaude-opus-4-20250514RegionglobalInput / 1M$15Output / 1M$75Context200KUpdatedAug 17, 2026
ProviderVertexProvider model IDclaude-opus-4@20250514RegionglobalInput / 1M$15Output / 1M$75Context200KUpdatedAug 17, 2026
ProviderOpenRouterProvider model IDanthropic/claude-opus-4RegionglobalInput / 1M$15Output / 1M$75Context200KUpdatedAug 17, 2026
ProviderVertex (Anthropic)Provider model IDclaude-opus-4@20250514RegionglobalInput / 1M$15Output / 1M$75Context200KUpdatedAug 17, 2026
ProviderMerge GatewayProvider model IDanthropic/claude-opus-4-20250514RegionglobalInput / 1M$15Output / 1M$75Context200KUpdatedAug 17, 2026
ProviderDigitalOceanProvider model IDanthropic-claude-opus-4RegionglobalInput / 1M$15Output / 1M$75Context200KUpdatedAug 17, 2026
ProviderZenMuxProvider model IDanthropic/claude-opus-4RegionglobalInput / 1M$15Output / 1M$75Context200KUpdatedAug 17, 2026
Provider302.AIProvider model IDclaude-opus-4-20250514RegionglobalInput / 1M$15Output / 1M$75Context200KUpdatedAug 17, 2026
ProviderVercel AI GatewayProvider model IDanthropic/claude-opus-4RegionglobalInput / 1M$15Output / 1M$75Context200KUpdatedAug 17, 2026
ProviderAbacusProvider model IDclaude-opus-4-20250514RegionglobalInput / 1M$15Output / 1M$75Context200KUpdatedAug 17, 2026

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

Claude Opus 4 Runtime Performance

Provider-specific output speed and catalog latency for Claude Opus 4. Runtime does not affect the capability score.

3 rows
Columns

Show columns

Sort by
Provider
Output Speed
Catalog Latency
Max Input
Max Output
Updated
ProviderBedrockOutput Speed120 tok/sCatalog Latency0.5 sMax Input200KMax Output128KUpdatedAug 17, 2026
ProviderAnthropicOutput Speed100 tok/sCatalog Latency0.5 sMax Input200KMax Output32KUpdatedAug 17, 2026
ProviderGoogleOutput Speed42 tok/sCatalog Latency0.4 sMax Input200KMax Output128KUpdatedAug 17, 2026

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

Claude Opus 4 Specifications

Technical details for the model's default version.

Version
Claude Opus 4
Released
May 22, 2025
Knowledge cutoff
Mar 31, 2025
Parameters
N/A
Context window
200K
Max output
32K
Inputs
image, pdf, text
Outputs
text
Open weights
No
License
Proprietary

Claude Opus 4 Versions

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

1 rows
Columns

Show columns

Sort by
Version
Released
LLMBoard
Parameters
Context
Max output
Open weights
License
VersionClaude Opus 4ReleasedMay 22, 2025LLMBoard45.3ParametersN/AContext200KMax output32KOpen weightsNoLicenseProprietary

Claude Opus 4 vs nearby models

Open a comparison with the three ranked models immediately above and below this model.

Claude Opus 4vsGrok 4.1Claude Opus 4vsMiMo V2.5 ProClaude Opus 4vsGPT-OSS-20BClaude Opus 4vsQwen3 VL 235B A22B ThinkingClaude Opus 4vsClaude Haiku 4.5Claude Opus 4vsGPT-5-mini

Models similar to Claude Opus 4

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

#114-0.1
AN

Claude Haiku 4.5

Anthropic

45.2 LLMBoard

DetailsCompare
#140-6.6
AN

Claude Sonnet 4

Anthropic

38.7 LLMBoard

DetailsCompare
#92+6.8
AN

Claude Opus 4.1

Anthropic

52.1 LLMBoard

DetailsCompare
#143-7.5
AN

Claude Sonnet 3.7

Anthropic

37.8 LLMBoard

DetailsCompare
#77+11.3
AN

Claude Sonnet 4.5

Anthropic

56.6 LLMBoard

DetailsCompare
#167-14.0
AN

Claude Sonnet 3.5

Anthropic

31.4 LLMBoard

DetailsCompare

What is Claude Opus 4?

Key information about Claude Opus 4 and its available data.

Claude Opus 4 is Anthropic's most powerful model and the world's best coding model, part of the Claude 4 family. It delivers sustained performance on complex, long-running tasks and agent workflows. Opus 4 excels at coding, advanced reasoning, and can use tools (like web search) during extended thinking.

It supports parallel tool execution and has improved memory capabilities.

Data as of 2026-08-17.

FAQ

Common questions about Claude Opus 4.

When was Claude Opus 4 released?

Claude Opus 4's default version was released on May 22, 2025.

How much does Claude Opus 4 cost?

No official standard PAYG price is currently available for Claude Opus 4. The lowest tracked third-party offer starts at $13 input and $64 output via Poe.

Who created Claude Opus 4?

Claude Opus 4 was created by Anthropic.

What is the context window for Claude Opus 4?

The default version has a 200K token context window.

Is Claude Opus 4 open weight?

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

How many API providers offer Claude Opus 4?

13 provider offerings are linked to the default version.

What models should I compare Claude Opus 4 with?

Nearby ranked alternatives include Grok 4.1, MiMo V2.5 Pro, GPT-OSS-20B.