llmboard.aiLeaderboard Center
Overall
Overall RankingOpen Models
Tools
Model DirectoryCompare Models
Capabilities
CodingReasoningMathKnowledgeInstruction Following
Price & Efficiency
Price & ValueCapability vs. PriceRuntime Performance
Modalities
Image GenerationVideo GenerationSpeech ModelsEmbeddings
Core Benchmarks
GPQAMMLU-ProAIME 2025SWE-Bench VerifiedMMLUHumanity's Last ExamLiveCodeBenchMATHHumanEvalMMMU-ProView all benchmarks
Methods
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

Model vendor

Anthropic

AI safety company

Updated Aug 11, 2026. Data as of 2026-08-11

Website
Models20
Versions27
Open defaults0
CountryUS

On this page

  • Models
  • Scores
  • Highlights
  • About
  • FAQ

Anthropic models

Default-version specifications and scored-version capability values are labeled separately.

20 rows
Columns

Show columns

ANClaude Opus 5AnthropicClaude Opus 597.460.0%1MClosed weightsJul 24, 2026Claude Opus 5
ANClaude Fable 5AnthropicClaude Fable 595.840.0%1MClosed weightsJun 9, 2026Claude Fable 5
ANClaude MythosAnthropicClaude Mythos Preview93.680.0%N/AClosed weightsN/AClaude Mythos Preview
ANClaude Opus 4.8AnthropicClaude Opus 4.887.960.0%1MClosed weightsMay 28, 2026Claude Opus 4.8
ANClaude Opus 4.7AnthropicClaude Opus 4.784.260.0%1MClosed weightsApr 16, 2026Claude Opus 4.7
ANClaude Sonnet 5AnthropicClaude Sonnet 584.060.0%1MClosed weightsJun 30, 2026Claude Sonnet 5
ANClaude Opus 4.6AnthropicClaude Opus 4.679.680.0%1MClosed weightsFeb 5, 2026Claude Opus 4.6
ANClaude Sonnet 4.6AnthropicClaude Sonnet 4.672.660.0%1MClosed weightsFeb 17, 2026Claude Sonnet 4.6
ANClaude Opus 4.5AnthropicClaude Opus 4.569.560.0%200KClosed weightsNov 24, 2025Claude Opus 4.5
ANClaude Sonnet 4.5AnthropicClaude Sonnet 4.556.080.0%200KClosed weightsSep 29, 2025Claude Sonnet 4.5
ANClaude Opus 4.1AnthropicClaude Opus 4.152.480.0%200KClosed weightsAug 5, 2025Claude Opus 4.1
ANClaude Opus 4AnthropicClaude Opus 446.480.0%200KClosed weightsMay 22, 2025Claude Opus 4
ANClaude Haiku 4.5AnthropicClaude Haiku 4.545.580.0%200KClosed weightsOct 15, 2025Claude Haiku 4.5
ANClaude Sonnet 4AnthropicClaude Sonnet 439.580.0%200KClosed weightsMay 22, 2025Claude Sonnet 4
ANClaude Sonnet 3.7AnthropicClaude 3.7 Sonnet38.7100.0%200KClosed weightsFeb 24, 2025Claude 3.7 Sonnet
ANClaude Sonnet 3.5AnthropicClaude 3.5 Sonnet32.180.0%200KClosed weightsOct 22, 2024Claude 3.5 Sonnet
ANClaude Opus 3AnthropicClaude 3 Opus16.780.0%200KClosed weightsFeb 29, 2024Claude 3 Opus
ANClaude Haiku 3.5AnthropicClaude 3.5 Haiku9.380.0%200KClosed weightsOct 22, 2024Claude 3.5 Haiku
ANClaude Sonnet 3AnthropicClaude 3 Sonnet3.580.0%200KClosed weightsFeb 29, 2024Claude 3 Sonnet
ANClaude Haiku 3AnthropicClaude 3 Haiku0.080.0%200KClosed weightsMar 13, 2024Claude 3 Haiku

Anthropic capability scores

Each unique model uses its latest scored version.

Anthropic LLMBoard scores

Anthropic Highlights

Leading Anthropic models by score, price and context window.

Top scoreClaude Opus 597.4 LLMBoardLowest official inputClaude Haiku 4.5$1.0 / 1MLargest contextClaude Fable 51M tokens
Open-weight defaults0of 20 models

What is Anthropic?

Background and model catalog information for Anthropic.

AI safety company

Model ownership is separate from API hosting. One model can be offered by multiple API providers with different prices.

Vendor
Anthropic
Models
20
Versions
27
Country
US
Founded
Not available

Catalog data as of 2026-08-11.

FAQ

Common questions about Anthropic.

What is Anthropic's highest-ranked model?

Claude Opus 5 currently has the strongest LLMBoard score from this vendor.

How many Anthropic models are tracked?

The catalog contains 20 independently selectable Anthropic models and 27 versions.

Does Anthropic host every listed model API?

Not necessarily. Vendor identifies the model developer; API providers are tracked separately.

Does Anthropic publish open-weight models?

No current default version is marked as open weight.