GPT-5.4 Pro (xhigh)
ModelActiveby OpenAI · family “gpt-pro-xhigh”
Epoch Capabilities Index
Not scored by Epoch AI
Released
5 Mar 2026
Context window
Unknown
Max output
Unknown
Input $ / 1M tokens
Unknown
Output $ / 1M tokens
Unknown
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 | 82.5% ±2.3 | 88% | xhigh | 13 Jun 2026 | Eval log ↗ |
| FrontierMath-Tier-4-v2-Private | math | 58.5% ±7.8 | 60% | xhigh | 13 Jun 2026 | Eval log ↗ |
| Chess Puzzles | games | 58.6% ±5.0 | 81% | xhigh | 19 Mar 2026 | Epoch ↗ |
| SimpleQA Verified | knowledge | 46.3% ±1.6 | 61% | xhigh | 27 Aug 2026 | Eval log ↗ |
| ARC-AGI-2 | reasoning | 83.3% | 88% | xhigh | — | External ↗ |
| FrontierMath-2025-02-28-Privatesuperseded | math | 50.0% ±2.9 | 95% | xhigh | 6 Mar 2026 | Epoch ↗ |
| GPQA diamond | science | 94.6% ±1.6 | 99% | xhigh | 20 Mar 2026 | Epoch ↗ |
| ARC-AGI | reasoning | 94.5% | 96% | xhigh | — | 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
This model has no public API price listing
0 recorded prices on — (OpenRouter listing); re-read on every data refresh, most recently 8h ago. Steps show when the price changed.
Events
- BenchmarkEpoch AI evaluates GPT-5.4 Pro (xhigh)Epoch AI Benchmarking Hub
- Model launchMajorOpenAI releases GPT-5.4 Pro (xhigh)Epoch AI Benchmarking Hub