GPT-5 Pro
ModelActiveby 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
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)
| 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 recorded prices on 1 Nov 2025 (OpenRouter listing + Internet Archive snapshots); re-read on every data refresh, most recently 8h ago. Steps show when the price changed.
Events
- Model launchMajorOpenAI releases GPT-5 ProEpoch AI Benchmarking Hub