Claude 3.5 HaikuvsGPT-5.3-Codex

Claude 3.5 Haiku
GPT-5.3-Codex
Benchmarks
Nonsense detection
BullshitBench v2
50%Best
24%
Coding
SWE-Bench Verified
40.6%
Next.js coding
Next.js Evals
83%
Science
GPQA Diamond
41.6%
Community preference (code)
Arena Elo (Code)
1406
Overview
CompanyAnthropicOpenAI
Release dateOct 22 2024Feb 5 2026
AccessProprietaryProprietary

Which is better: Claude 3.5 Haiku or GPT-5.3-Codex?

Claude 3.5 Haiku leads GPT-5.3-Codex on 1 of the 1 benchmark they both report (BullshitBench v2). Claude 3.5 Haiku shipped 471 days before GPT-5.3-Codex, 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-5.3-Codex at 24%.

Frequently asked questions

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

GPT-5.3-Codex was released by OpenAI on Feb 5 2026.

Other comparisons