Claude 3 HaikuvsGPT-4o

Claude 3 Haiku
GPT-4o
Specifications
Context window
128k
Benchmarks
Nonsense detection
BullshitBench v2
10%
12%Best
Science
GPQA Diamond
33.3%
49.9%Best
Overview
CompanyAnthropicOpenAI
Release dateMar 4 2024May 13 2024
AccessProprietaryProprietary

Which is better: Claude 3 Haiku or GPT-4o?

GPT-4o leads Claude 3 Haiku on 2 of the 2 benchmarks they both report (BullshitBench v2, GPQA Diamond). Claude 3 Haiku shipped 70 days before GPT-4o, so benchmark comparisons should account for the intervening progress.

Published specifications for these two models are limited — see each model page for the latest details.

On BullshitBench v2, GPT-4o leads at 12% vs Claude 3 Haiku at 10%. On GPQA Diamond, GPT-4o leads at 49.9% vs Claude 3 Haiku at 33.3%.

Frequently asked questions

Claude 3 Haiku was released by Anthropic on Mar 4 2024.

GPT-4o was released by OpenAI on May 13 2024.

GPT-4o leads on GPQA Diamond — Claude 3 Haiku 33.3% vs GPT-4o 49.9%.

Other comparisons