OpenAI
gpt-5.4-pro-2026-03-05
Made by OpenAI. Released 2026-03-05. Accessibility not recorded. We hold no price for this model: no seller we can read lists it any more, so what follows is what was measured, not what it cost.
What it scores, by house
| Benchmark | House | Score | Evaluated | Scaffold |
|---|---|---|---|---|
| chess puzzles | Epoch AI | 0.6±0.05 | 2026-03-19 | xhigh |
| frontiermath | Epoch AI | 0.5±0.03 | 2026-03-06 | xhigh |
| frontiermath tier 4 v2 | Epoch AI | 0.6±0.08 | 2026-06-13 | xhigh |
| frontiermath tiers 1 3 v2 | Epoch AI | 0.8±0.02 | 2026-06-13 | xhigh |
| gpqa diamond | Epoch AI | 0.9±0.02 | 2026-03-20 | xhigh |
| simpleqa verified | Epoch AI | 0.5±0.02 | 2026-08-27 | xhigh |
| arc aginear its ceiling | collected by Epoch AI | 0.9 | — | xhigh |
| arc agi 2 | collected by Epoch AI | 0.8 | — | xhigh |
| critpt | collected by Epoch AI | 0.3 | — | xhigh |
| enigma eval | collected by Epoch AI | 0.2 | — | unknown |
| hle | collected by Epoch AI | 0.4 | — | unknown |
| simplebench | collected by Epoch AI | 0.7 | — | unknown |
| weirdml | collected by Epoch AI | 0.6 | — | none |
These scores are not comparable between houses and are not added up. A score is dated by when it was evaluated, not when the model was released, and a score without its scaffold is not a measurement — which is why both are printed.