Key Specifications

SpecificationGPT-4oClaude 3.5 Haiku
Vendoropenaianthropic
Version4o3.5-haiku
Release Date2024-05-132024-11-04
Context Window128000 tokens200000 tokens
Input Modalitiestext, image, audiotext, image
Output Modalitiestext, audiotext
LicenseProprietaryProprietary
SOC2
HIPAA
GDPR
ISO 27001

Benchmark Results

BenchmarkGPT-4oClaude 3.5 HaikuWinner
ARC91.8Claude 3.5 Haiku
BBH83.170.2GPT-4o
GPQA31.1Claude 3.5 Haiku
GSM8K95.875.5GPT-4o
HUMANEVAL90.273.8GPT-4o
IFEVAL73.6Claude 3.5 Haiku
MATH76.653GPT-4o
MMLU88.777.6GPT-4o
MUSR52.3Claude 3.5 Haiku
WINOGRANDE83.8Claude 3.5 Haiku

Pricing Comparison

Tier (per Mtok)GPT-4oClaude 3.5 Haiku
Input$2.5$0.8
Output$10$4
Cache Read$1.25$0
Cache Write$2.5$0

GPT-4o vs Claude 3.5 Haiku

Model Overview

GPT-4o and Claude 3.5 Haiku are both notable options in the AI model market. This page compares their benchmarks, pricing, and compliance.

Key Specifications

VendorRelease DateContext WindowLicense
Openai / Anthropic2024-05-13 / 2024-11-04128K / 200KProprietary / Proprietary

Benchmark Performance

BenchmarkGPT-4oClaude 3.5 HaikuWinner
ARC91.8B
BBH (BIG-Bench Hard)83.170.2A
GPQA31.1B
GSM8K (Grade School Math 8K)95.875.5A
HumanEval90.273.8A
IFEval73.6B
MATH76.653.0A
MMLU (Massive Multitask Language Understanding)88.777.6A
MUSR52.3B
WinoGrande83.8B

Pricing Comparison

InputOutputCache ReadCache Write
— / —— / —— / —— / —

per million tokens — A / B

Strengths & Weaknesses

GPT-4o

  • ✅ MMLU score 88.7, strong knowledge reasoning.
  • ✅ HumanEval 90.2, excellent code generation.
  • ✅ GSM8K 95.8, robust math reasoning.
  • ✅ Input Modalities: text, image, audio.
  • ⚠️ Proprietary, not self-hostable.

Claude 3.5 Haiku

  • ✅ Reliable general-purpose model.
  • ⚠️ Proprietary, not self-hostable.

Editor’s Take

GPT-4o and Claude 3.5 Haiku each have their strengths. Choose based on workload (code, long context, vision), referencing the tables above.

FAQ

Which model is better for coding tasks?

Refer to the HumanEval benchmark table; the model with a higher score is better suited for coding tasks.

Which model is cheaper?

Refer to the pricing comparison table above; the model with lower input/output prices is more cost-effective.

Which has a longer context window?

Refer to the key specifications table; the model with a larger context window is better for long documents.

References

Editor's Take

See Editor's Take section.