LIVE INTELLIGENCE · part of the Xentir AI Index

GPT-5 (07 Aug 2025) vs GPT-5 Pro

Name: GPT-5 (07 Aug 2025) vs GPT-5 Pro — benchmark results
Creator: Epoch AI
License: https://creativecommons.org/licenses/by/4.0/

GPT-5 (07 Aug 2025) · OpenAI, released 2025-08-07
GPT-5 Pro · OpenAI, released 2025-10-07

“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 2026-09-09 · Methodology · Data Sources

GPT-5 Pro leads on more of the 2 benchmarks where both are measured — GPT-5 Pro on 2. The remaining 7 of 9 tracked benchmarks cannot be compared: 7 have a result for only one of the two models, 0 for neither. Nothing on this page is estimated to fill those in.

Head-to-head

Measured on 2 of 9 tracked benchmarks for both models — GPT-5 Pro leads on 2.

Benchmark	GPT-5 (07 Aug 2025)	GPT-5 Pro	Leads
Epoch Capabilities Index (ECI)	150.0	150.3	GPT-5 Pro
SWE-bench Verified	0.736 (high)	Not measured	Comparison unavailable — GPT-5 Pro has no published result
GPQA Diamond	0.862 (high)	Not measured	Comparison unavailable — GPT-5 Pro has no published result
MATH Level 5	0.981 (high)	Not measured	Comparison unavailable — GPT-5 Pro has no published result
OTIS Mock AIME 2024-2025	0.914 (high)	Not measured	Comparison unavailable — GPT-5 Pro has no published result
FrontierMath	0.324 (high)	Not measured	Comparison unavailable — GPT-5 Pro has no published result
FrontierMath Tier 4	0.125 (high)	0.146 (high)	GPT-5 Pro
SimpleQA Verified	0.501 (high)	Not measured	Comparison unavailable — GPT-5 Pro has no published result
Chess Puzzles	0.370 (high)	Not measured	Comparison unavailable — GPT-5 Pro has no published result

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.

What remains uncertain

GPT-5 Pro has no published result on Chess Puzzles, FrontierMath, GPQA Diamond, MATH Level 5, OTIS Mock AIME 2024-2025, SWE-bench Verified, SimpleQA Verified.

A missing result means Xentir has not found one published by the source it cites, not that the model performs badly. See Data Sources.

Reference price

Per 1M tokens	GPT-5 (07 Aug 2025)	GPT-5 Pro
Output	—	$120.00

List price as published by the vendor. Xentir does not verify negotiated or enterprise rates, and price is not a measure of capability — see Data Sources.

Full profiles

GPT-5 (07 Aug 2025) → · GPT-5 Pro → · the full AI Model Rankings table