Claude 3.5 HaikuvsGPT-5.1

Claude 3.5 Haiku
GPT-5.1
Benchmarks
Nonsense detection
BullshitBench v2
50%Best
25%
Coding
SWE-Bench Verified
40.6%
76.3%Best
Science
GPQA Diamond
41.6%
88.1%Best
Multimodal
MMMU
76%
Community preference (code)
Arena Elo (Code)
1391
Overview
CompanyAnthropicOpenAI
Release dateOct 22 2024Nov 12 2025
AccessProprietaryProprietary

Which is better: Claude 3.5 Haiku or GPT-5.1?

GPT-5.1 leads Claude 3.5 Haiku on 2 of the 3 benchmarks they both report (BullshitBench v2, SWE-Bench Verified, GPQA Diamond). Claude 3.5 Haiku shipped 386 days before GPT-5.1, 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-5.1 at 25%. On SWE-Bench Verified, GPT-5.1 leads at 76.3% vs Claude 3.5 Haiku at 40.6%. On GPQA Diamond, GPT-5.1 leads at 88.1% vs Claude 3.5 Haiku at 41.6%.

Frequently asked questions

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

GPT-5.1 was released by OpenAI on Nov 12 2025.

GPT-5.1 leads on SWE-Bench Verified — Claude 3.5 Haiku 40.6% vs GPT-5.1 76.3%.

GPT-5.1 leads on GPQA Diamond — Claude 3.5 Haiku 41.6% vs GPT-5.1 88.1%.

Other comparisons