Home Model series GPT unsuffixed models GPT-5.2 GPT-5.2 · AIME · 2025 edition · Scores and configurations GPT-5.2 · AIME · 2025 edition · Scores and configurations GPT-5.2 record for AIME · 2025 edition. 2 score records for this release, including 2 exact values (may include historical records). Includes 1 source location.
Scores and evaluation conditions GPT-5.2 · AIME scores and configurations Metric and score Configuration and evaluation conditions Sources Accuracy 100% Reported 100.0% · Unit % Published Unconfirmed
GPT-5.2 Thinking (xhigh) Settings Highest available API reasoning effort xhigh, except professional benchmark tasks. Unknowns none recorded Tools Tools forbidden Reasoning budget xhigh Framework not recorded Protocol AIME 2025, no tools. Conditions Highest available API reasoning effort xhigh; research environment. View this score in rankings Accuracy 100% Reported 100.0% · Unit % Published Unconfirmed
GPT-5.2 Pro (xhigh) Settings Pro variant; highest available API reasoning effort xhigh except professional benchmark tasks. Unknowns The article does not publish a Pro GDPval result under the same heavy setting as the Thinking result; reported row retained as printed. Tools Tools forbidden Reasoning budget xhigh Framework not recorded Protocol AIME 2025, no tools. Conditions GPT-5.2 Pro; highest available API effort xhigh. View this score in rankings
Benchmark versions and metrics Aliases AIME 2025
Accuracy · % · Higher is better