Claude 3.5 HaikuvsGPT-4.1

Claude 3.5 Haiku
GPT-4.1
Benchmarks
Nonsense detection
BullshitBench v2
50%Best
14%
Coding
SWE-Bench Verified
40.6%
Science
GPQA Diamond
41.6%
Overview
CompanyAnthropicOpenAI
Release dateOct 22 2024Apr 14 2025
AccessProprietaryProprietary

Which is better: Claude 3.5 Haiku or GPT-4.1?

Claude 3.5 Haiku leads GPT-4.1 on 1 of the 1 benchmark they both report (BullshitBench v2). Claude 3.5 Haiku shipped 174 days before GPT-4.1, 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, Claude 3.5 Haiku leads at 50% vs GPT-4.1 at 14%.

Frequently asked questions

Claude 3.5 Haiku was released by Anthropic on Oct 22 2024.

GPT-4.1 was released by OpenAI on Apr 14 2025.

Other comparisons