Claude 3 HaikuvsGPT-5.2

Claude 3 Haiku
GPT-5.2
Benchmarks
Nonsense detection
BullshitBench v2
10%
38%Best
Coding
SWE-Bench Verified
80%
Abstract reasoning
ARC-AGI-2
52.9%
Science
GPQA Diamond
33.3%
92.4%Best
Community preference
Arena Elo (Text)
1476
Community preference (code)
Arena Elo (Code)
1419
Overview
CompanyAnthropicOpenAI
Release dateMar 4 2024Dec 11 2025
AccessProprietaryProprietary

Which is better: Claude 3 Haiku or GPT-5.2?

GPT-5.2 leads Claude 3 Haiku on 2 of the 2 benchmarks they both report (BullshitBench v2, GPQA Diamond). Claude 3 Haiku shipped 647 days before GPT-5.2, 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-5.2 leads at 38% vs Claude 3 Haiku at 10%. On GPQA Diamond, GPT-5.2 leads at 92.4% vs Claude 3 Haiku at 33.3%.

Frequently asked questions

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

GPT-5.2 was released by OpenAI on Dec 11 2025.

GPT-5.2 leads on GPQA Diamond — Claude 3 Haiku 33.3% vs GPT-5.2 92.4%.

Other comparisons