Claude 4 Opus

Anthropic の最高級言語モデルで、世界最高のプログラミングモデルと位置付けられています。複数のベンチマークで新記録を樹立し、SWE-bench で 72.5%、Terminal-bench で 43.2% を達成しました。200K のコンテキストウィンドウと高度なツール統合をサポートし、中上級開発者レベルの効率で 7 時間連続してプログラミング作業が可能で、最も複雑なコード開発と分析タスクに適しています。

Intelligence(Medium)

Speed(Relatively Slow)

Input Supported Modalities

Yes

Is Reasoning Model

200,000

Context Window

128,000

Maximum Output Tokens

Knowledge Cutoff

Go Compare

Pricing

￥108 /M tokens

Input

￥540 /M tokens

Output

￥216 /M tokens

Blended Price

Quick Simple Comparison

Input

Output

Claude 4 Sonnet

￥3

Claude 4 Opus (Extended Thinking)

￥15

Claude Opus 4.1

￥15

Basic Parameters

Claude 4 OpusTechnical Parameters

Parameter Count

Not Announced

Context Length

200.00k tokens

Training Data Cutoff

Open Source Category

Proprietary

Multimodal Support

Text, Image

Throughput

120

Release Date

2025-05-22

Response Speed

62.37,708 tokens/s

Benchmark Scores

Below is the performance of Claude 4 Opus in various standard benchmark tests. These tests evaluate the model's capabilities in different tasks and domains.

Intelligence Index

Large Language Model Intelligence Level

57.68

Large Language Model Intelligence Level

Coding Index

Indicator of AI model performance on coding tasks

47.52

Indicator of AI model performance on coding tasks

Math Index

Capability indicator in solving mathematical problems, mathematical reasoning, or performing math-related tasks

75.2

Capability indicator in solving mathematical problems, mathematical reasoning, or performing math-related tasks

MMLU Pro

Massive Multitask Multimodal Understanding - Testing understanding of text, images, audio, and video

GPQA

Graduate Physics Questions Assessment - Testing advanced physics knowledge with diamond science-level questions

70.1

Graduate Physics Questions Assessment - Testing advanced physics knowledge with diamond science-level questions

HLE

The model's comprehensive average score on the Hugging Face Open LLM Leaderboard

5.9

The model's comprehensive average score on the Hugging Face Open LLM Leaderboard

LiveCodeBench

Specific evaluation focused on assessing large language models' ability in real-world code writing and solving programming competition problems

54.2

Specific evaluation focused on assessing large language models' ability in real-world code writing and solving programming competition problems

SciCode

The model's capability in code generation for scientific computing or specific scientific domains

40.9

The model's capability in code generation for scientific computing or specific scientific domains

HumanEval

Score achieved by the AI model on the specific HumanEval benchmark test set

Math 500 Score

Score on the first 500 larger, more well-known mathematical benchmark tests

94.1

Score on the first 500 larger, more well-known mathematical benchmark tests

AIME Score

An indicator measuring an AI model's ability to solve high-difficulty mathematical competition problems (specifically AIME level)

56.3

An indicator measuring an AI model's ability to solve high-difficulty mathematical competition problems (specifically AIME level)

Output tokens/million

Output tokens/million

Output tokens/million

Output tokens/million

Output tokens/million

Output tokens/million

33k

Context Length

Gemini 2.0 Flash Lite (Preview)

Output tokens/million

Output tokens/million

8192

Context Length

Empowering the Future, Your AI Solution Knowledge Base

English 简体中文繁體中文にほんご