Claude 3.5 Haiku

Claude 3.5 HaikuはAnthropicが提供する最速のモデルで、手頃な価格で高度なコーディング、ツールの使用、推論機能を提供します。このモデルは、ユーザー向けの製品、専用のサブエージェントタスク、大量のデータからの個別化された体験の生成に優れています。特に、コード補完、対話型チャットボット、データ抽出、リアルタイムのコンテンツ審査に適しています。

Intelligence(Relatively Weak)

Speed(Relatively Slow)

Input Supported Modalities

Is Reasoning Model

200,000

Context Window

200,000

Maximum Output Tokens

Knowledge Cutoff

Pricing

￥5.76 /M tokens

Input

￥28.8 /M tokens

Output

￥11.52 /M tokens

Blended Price

Quick Simple Comparison

Claude 4 Opus (Extended Thinking)

￥15

Claude 3 Opus

￥15

Claude 4 Sonnet

￥3

Basic Parameters

Claude 3.5 HaikuTechnical Parameters

Parameter Count

Not Announced

Context Length

200.00k tokens

Training Data Cutoff

Open Source Category

Proprietary

Multimodal Support

Text Only

Throughput

104

Release Date

2024-10-22

Response Speed

66.382,095 tokens/s

Benchmark Scores

Below is the performance of Claude 3.5 Haiku in various standard benchmark tests. These tests evaluate the model's capabilities in different tasks and domains.

Intelligence Index

Large Language Model Intelligence Level

34.74

Large Language Model Intelligence Level

Coding Index

Indicator of AI model performance on coding tasks

29.43

Indicator of AI model performance on coding tasks

Math Index

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

37.7

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

63.4

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

40.8

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

3.5

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

31.4

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

27.4

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

85.9

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

72.1

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)

3.3

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

Featured Recommended AI Models

Output tokens/million

Output tokens/million

8192

Context Length

Qwen2.5 Coder Instruct 32B

Output tokens/million

Output tokens/million

Context Length

Gemini 1.5 Pro (May '24)

Output tokens/million

Context Length

Llama 3.2 Instruct 11B (Vision)