Home Model series GPT unsuffixed models GPT-5.2 GPT-5.2 · ARC-AGI-2 · Verified;题集组成未在发布表中说明 · Scores and configurations GPT-5.2 · ARC-AGI-2 · Verified;题集组成未在发布表中说明 · Scores and configurations GPT-5.2 record for ARC-AGI-2 · Verified;题集组成未在发布表中说明. 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 · ARC-AGI-2 scores and configurations Metric and score Configuration and evaluation conditions Sources Accuracy 52.9% Reported 52.9% · Unit % Published Unconfirmed
GPT-5.2 Thinking (xhigh) Settings Highest available API reasoning effort xhigh, except professional benchmark tasks. Unknowns none recorded Tools Tool access not recorded Reasoning budget xhigh Framework not recorded Protocol ARC-AGI-2 Verified. Conditions Highest available API reasoning effort xhigh. View this score in rankings Accuracy 54.2% Reported 54.2% · Unit % Published Unconfirmed
GPT-5.2 Pro (high) Settings ARC-AGI-2 54.2% 的官方表列明确标为 GPT-5.2 Pro (high),不外推为 Xhigh。 Unknowns 该行未注明完整采样设置与harness。 Tools Tool access not recorded Reasoning budget high Framework not recorded Protocol ARC-AGI-2 Verified. Conditions The article labels Pro as high for this row; retained as printed. View this score in rankings
Benchmark versions and metrics Aliases ARC-AGI-2 (Verified)
Accuracy · % · Higher is better