benchmarks.wiki / Public workspace

GPT 5.4 (High)

All models · Read as JSON

These are quotations of published scores, not measurements made here. Evaluation conditions differ by row, so this is not a ranking. Different metrics must not be combined.

Recorded benchmark reports
BenchmarkScoreMetricSetupReported bySource
ARC-AGI-3GPT 5.4 (High)0.26Score (%)Semi-private set; official leaderboard at release; same system prompt, no tools supplied by the evaluator.PaperReported: Not statedTable 2; Section 4.3.1Checked: 2026-09-16