GPT-5 Pro

ModelActive

by OpenAI · family “gpt-pro”

GPT-5 Pro is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience. It is optimized for complex tasks that require step-by-step reasoning, instruction following, and... (description from the OpenRouter listing)

in: imagein: textin: fileout: textReasoningTool useStructured output

Epoch Capabilities Index

150.3 #45 of 268

90% CI 148.5 – 152.8

Listing ↗

Released

7 Oct 2025

Context window

400K tokens

Max output

128K tokens

Input $ / 1M tokens

$15.0

Output $ / 1M tokens

$120.0

Cached input $ / 1M

Unknown

Each benchmark shown separately with its own source

Benchmark results (8)

All benchmarks

Benchmark	Domain	Score	vs best recorded	Setting	Run	Source
FrontierMath-Tiers-1-3-v2-Private	math	55.8% ±2.9	60%	high	12 Jun 2026	Eval log ↗
FrontierMath-Tier-4-v2-Private	math	19.5% ±6.3	20%	high	12 Jun 2026	Eval log ↗
FrontierMath-Tier-4-2025-07-01-Privatesuperseded	math	14.6% ±5.1	30%	high	9 Oct 2025	Epoch ↗
ARC-AGI-2	reasoning	18.3%	19%	unknown	—	External ↗
HLE	knowledge	31.6%	58%	unknown	—	External ↗
WeirdML	coding	60.4% ±0.0	65%	high	—	External ↗
SimpleBench	reasoning	61.6%	75%	high	—	External ↗
ARC-AGI	reasoning	70.2%	71%	high	—	External ↗

Source: Epoch AI Benchmarking Hub (CC BY 4.0). “External” rows are leaderboard results Epoch collects from third parties. Best reported setting per benchmark is shown.

API list price over time

Price history

$ per 1M tokens

12 observations (OpenRouter listing + Internet Archive snapshots). History accumulates with every ingest run; a single point means no change has been observed yet.