Key Specifications

Vendoranthropic
Version3.5-haiku
Release Date2024-11-04
Context Window200000 tokens
Input Modalitiestext, image
Output Modalitiestext
LicenseProprietary
Documentationhttps://docs.anthropic.com/claude/docs

Benchmark Performance

Benchmark Score Unit Evaluated At Notes Source
MMLU 77.6 % 2024-11-04 5-shot view
HUMANEVAL 73.8 pass@1 2024-11-04 view
GSM8K 75.5 % 2024-11-04 0-shot CoT view
MATH 53 % 2024-11-04 0-shot CoT view
BBH 70.2 % 2024-11-04 3-shot CoT view
GPQA 31.1 % 2024-11-04 0-shot view
IFEVAL 73.6 % 2024-11-04 prompt_strict view
ARC 91.8 % 2024-11-04 challenge view
MUSR 52.3 % 2024-11-04 0-shot view
WINOGRANDE 83.8 % 2024-11-04 0-shot view

Pricing

Tier Price Currency
Input$0.8 / MtokUSD
Output$4 / MtokUSD
Cache Read$0 / MtokUSD
Cache Write$0 / MtokUSD

Source: https://www.anthropic.com/pricing · as of 2024-11-04

Compliance

  • Data Residency: US
  • SOC2: ✓
  • HIPAA: ✗
  • GDPR: ✓
  • ISO 27001: ✗

Claude 3.5 Haiku

Model Overview

Anthropic Claude 3.5 Haiku 经济型模型, 200K 上下文, 速度比 Sonnet 快 2 倍, 性能超越 Claude 3 Opus。

Core Specifications

Vendor Version Release Date Context Window Input Modalities Output Modalities License
Anthropic 3.5-haiku 2024-11-04 200K text, image text Proprietary

Benchmark Performance

Benchmark Score Unit Notes
MMLU (Massive Multitask Language Understanding) 77.6 % 5-shot
HumanEval 73.8 pass@1
GSM8K (Grade School Math 8K) 75.5 % 0-shot CoT
MATH 53.0 % 0-shot CoT
BBH (BIG-Bench Hard) 70.2 % 3-shot CoT
GPQA 31.1 % 0-shot
IFEval 73.6 % prompt_strict
ARC 91.8 % challenge
MUSR 52.3 % 0-shot
WinoGrande 83.8 % 0-shot

Pricing

Input Output Cache Read Cache Write

per million tokens

Strengths

  • Reliable general-purpose model.

Weaknesses

  • Proprietary, not self-hostable.

Use Cases

  • Code generation and debugging

References