LIVE INTELLIGENCE · part of the Xentir AI Index

GPT-5.4 vs GPT-5.4 Pro

GPT-5.4 · OpenAI, released 2026-03-05
GPT-5.4 Pro · OpenAI, released 2026-03-05

“Epoch AI, 'AI Benchmarking Hub'. Published online at epoch.ai. Retrieved from 'https://epoch.ai/benchmarks' [online resource].” · epoch.ai/benchmarks · Licensed CC BY 4.0 · data last verified 2026-07-26 · Methodology · Data Sources

Head-to-head

Measured on 6 of 9 tracked benchmarks for both models — GPT-5.4 Pro leads on 6.

Benchmark	GPT-5.4	GPT-5.4 Pro	Leads
Epoch Capabilities Index (ECI)	156.1	157.9	GPT-5.4 Pro
SWE-bench Verified	0.769 (high)	Not measured	Not measured on both
GPQA Diamond	0.933 (xhigh)	0.946 (xhigh)	GPT-5.4 Pro
MATH Level 5	Not measured	Not measured	Not measured on both
OTIS Mock AIME 2024-2025	0.953 (xhigh)	Not measured	Not measured on both
FrontierMath	0.476 (xhigh)	0.500 (xhigh)	GPT-5.4 Pro
FrontierMath Tier 4	0.271 (xhigh)	0.375 (web-app)	GPT-5.4 Pro
SimpleQA Verified	0.448 (xhigh)	0.478 (xhigh)	GPT-5.4 Pro
Chess Puzzles	0.440 (xhigh)	0.586 (xhigh)	GPT-5.4 Pro

Benchmark results measure specific tasks and should not be treated as a universal measure of model quality. A model with no row here for a benchmark has not been measured on it — that is left blank, never estimated.

Full profiles

GPT-5.4 → · GPT-5.4 Pro → · the full AI Model Rankings table