Values by metric family

Each value as the document printed it. Select a value for its source, its checks and its history.

KeyVerifiedUnverifiedDisputedCorrected read off a figure or stated in wordsA value opens its source and history.

M3 · Sabotage and sandbagging 1 value

M3 Sabotage and sandbagging: values about GPT-5.2
Evaluation and metricValueDocument
From other documents
Sabotage capabilityMean best-of-10 scoreRun by Apollo ResearchGPT-5.3-Codex System Card5 Feb 2026First reportedGPT-5.3-Codex System Card5 Feb 2026First reported

No restatements, risk determinations or revisions are recorded for GPT-5.2.