Claude 3.5 SonnetvsGPT-5-Codex

Claude 3.5 Sonnet
GPT-5-Codex
Benchmarks
Nonsense detection
BullshitBench v2
45%Best
39%
Coding
SWE-Bench Verified
33.4%
Science
GPQA Diamond
59.4%
Overview
CompanyAnthropicOpenAI
Release dateJun 20 2024Sep 15 2025
AccessProprietaryProprietary

Which is better: Claude 3.5 Sonnet or GPT-5-Codex?

Claude 3.5 Sonnet leads GPT-5-Codex on 1 of the 1 benchmark they both report (BullshitBench v2). Claude 3.5 Sonnet shipped 452 days before GPT-5-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 Sonnet leads at 45% vs GPT-5-Codex at 39%.

Frequently asked questions

Claude 3.5 Sonnet was released by Anthropic on Jun 20 2024.

GPT-5-Codex was released by OpenAI on Sep 15 2025.

Other comparisons