LIVE INTELLIGENCE · part of the Xentir AI Index

DeepSeek v4 Pro vs GPT-5.4 mini

DeepSeek v4 Pro OPEN WEIGHTS · DeepSeek, released 2026-04-24
GPT-5.4 mini · OpenAI, released 2026-03-17

“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 5 of 9 tracked benchmarks for both models — DeepSeek v4 Pro leads on 4, GPT-5.4 mini leads on 1.

Benchmark	DeepSeek v4 Pro	GPT-5.4 mini	Leads
Epoch Capabilities Index (ECI)	148.7	148.9	GPT-5.4 mini
SWE-bench Verified	0.776 (max)	Not measured	Not measured on both
GPQA Diamond	0.896 (max)	0.836 (high)	DeepSeek v4 Pro
MATH Level 5	Not measured	Not measured	Not measured on both
OTIS Mock AIME 2024-2025	0.967 (max)	0.872 (high)	DeepSeek v4 Pro
FrontierMath	Not measured	0.283 (high)	Not measured on both
FrontierMath Tier 4	Not measured	0.021 (high)	Not measured on both
SimpleQA Verified	0.570 (max)	0.286 (high)	DeepSeek v4 Pro
Chess Puzzles	0.200 (max)	0.180 (high)	DeepSeek v4 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

DeepSeek v4 Pro → · GPT-5.4 mini → · the full AI Model Rankings table