Claude 3 SonnetvsGPT-5.4

Claude 3 Sonnet
GPT-5.4
Benchmarks
Nonsense detection
BullshitBench v2
48%
Next.js coding
Next.js Evals
83%
Agentic terminal coding
Terminal-Bench 2.0
75.1%
Software engineering
Expert-SWE (Internal)
68.5%
General tool use
Toolathlon
54.6%
Web browsing
BrowseComp
82.7%
Cybersecurity
CyberGym
79%
Advanced math
FrontierMath · Tier 1–3
47.6%
Advanced math
FrontierMath · Tier 4
27.1%
Science
GPQA Diamond
40.4%
92.8%Best
Agentic computer use
OSWorld-Verified
75%
Knowledge work
GDPval (win/tie rate)
83%
Community preference
Arena Elo (Text)
1476
Community preference (code)
Arena Elo (Code)
1462
Overview
CompanyAnthropicOpenAI
Release dateMar 4 2024Mar 5 2026
AccessProprietaryProprietary

Which is better: Claude 3 Sonnet or GPT-5.4?

GPT-5.4 leads Claude 3 Sonnet on 1 of the 1 benchmark they both report (GPQA Diamond). Claude 3 Sonnet shipped 731 days before GPT-5.4, 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 GPQA Diamond, GPT-5.4 leads at 92.8% vs Claude 3 Sonnet at 40.4%.

Frequently asked questions

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

GPT-5.4 was released by OpenAI on Mar 5 2026.

GPT-5.4 leads on GPQA Diamond — Claude 3 Sonnet 40.4% vs GPT-5.4 92.8%.

Other comparisons