GPT-5.4 (High) — benchmark results
GPT-5.4 evaluated at the high reasoning-effort setting. Provider: OpenAI. Released 2026-03-06. Access: API.
Unified ELO 1915 ± 23, rank #54 of 1776 rated models, from 82 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| APEX v1 | 67.2 | Score (%) | 100 |
| CubeBench | 66.7 | Success Rate (%) | 100 |
| GENSTRAT | 85 | Alpha (chips/game) (self-reported) | 100 |
| LLM2014 Logic 2026-03 | 78.85 | Median Score | 100 |
| OpenCompass LLM - Language | 80.2 | Score (%) | 100 |
| OpenCompass Language - Creation | 82.5 | Score (%) | 100 |
| OpenCompass Language - NLP | 74.6 | Score (%) | 100 |
| OpenCompass Reasoning - Academic | 52 | Score (%) | 100 |
| Persuasion (Lechmazur) | 1.71 | Average Persuasion Strength | 100 |
| VTB | 29.17 | Score (self-reported) | 100 |
| UGI - Natural Intelligence | 71.25 | NatInt Score | 98.6 |
| UGI - Writing | 68.82 | Writing Score | 98.4 |
Interactive version: theaggregate.ai/model?slug=gpt-5-4-high · How the rankings work · Data refreshed daily, snapshot 2026-07-22.