DataLearner logo

GPT-5.4 ProvsGPT-5.2 Pro

Across 3 shared benchmarks, GPT-5.4 Pro leads overall: GPT-5.4 Pro wins 3, GPT-5.2 Pro wins 0, with 0 ties and an average score difference of +9.06.

OpenAI
GPT-5.4 Pro

OpenAI · 2026-03-05 · Multimodal model

OpenAI
GPT-5.2 Pro

OpenAI · 2025-12-11 · Reasoning model

GPT-5.4 Pro3 wins(100%)(0%)0 winsGPT-5.2 Pro

Benchmark scores

Grouped by capability, sorted by largest gap within each. 3 shared benchmarks.

Math and Reasoning

GPT-5.4 Pro 3/3
BenchmarkGPT-5.4 ProGPT-5.2 ProDiff
FrontierMath Tier 4 v258.5410 / 42Extra-High (No Tools)4614 / 42Extra-High (No Tools)+12.54
FrontierMath v282.467 / 58Extra-High (No Tools)7412 / 58Extra-High (No Tools)+8.46
FrontierMath - Tier 437.505 / 80Normal (With Tools + Internet)31.309 / 80Normal (With Tools + Internet)+6.20

Specs

FieldGPT-5.4 ProGPT-5.2 Pro
PublisherOpenAIOpenAI
Release date2026-03-052025-12-11
Model typeMultimodal modelReasoning model
ArchitectureDenseDense
ParametersNot availableNot available
Context length1M256K
Max output125KNot available

API pricing

Prices use DataLearner records when available; missing fields are not inferred.

ItemGPT-5.4 ProGPT-5.2 Pro
Text input$30 / 1M tokens$21 / 1M tokens
Text output$180 / 1M tokens$168 / 1M tokens

Summary

  • GPT-5.4 Proleads in:Math and Reasoning (3/3)

On average across the 3 shared benchmarks, GPT-5.4 Pro scores 9.06 higher.

Largest single-benchmark gap: FrontierMath Tier 4 v2 — GPT-5.4 Pro 58.54 vs GPT-5.2 Pro 46 (+12.54).

Page generated from structured model, pricing and benchmark records. No real-time LLM is used to write the prose.