Home Model series GPT unsuffixed models GPT unsuffixed models · ARC-AGI-2 · Verified;题集组成未在发布表中说明 · Release history GPT unsuffixed models · ARC-AGI-2 · Verified;题集组成未在发布表中说明 · Release history View scores, configurations, and disclosures for ARC-AGI-2 · Verified;题集组成未在发布表中说明 across 2 GPT unsuffixed models releases, ordered by release date.
Differences are calculated only for unique, active, exact values between direct predecessors when the unit, metric, and explicitly recorded configuration and conditions match.
2025-12-11 · 2 score records for this release, including 2 exact values (may include historical records)
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
2026-03-05 · 2 score records for this release, including 2 exact values (may include historical records)
Records for the direct predecessor do not provide matching conditions for a valid difference.
GPT-5.4 · ARC-AGI-2 scores and configurations Metric and score Configuration and evaluation conditions Sources Accuracy 83.3% Reported 83.3% · Unit % Published Unconfirmed
GPT-5.4 Pro Settings Pro model variant; the article reports Pro separately from GPT-5.4. Unknowns The Pro column is not a reasoning-effort label; the exact effort for each Pro evaluation is not separately stated. Tools Tool access not recorded Reasoning budget not recorded Framework not recorded Protocol ARC-AGI-2 Verified. Conditions Official release table labels GPT-5.4 Pro; research evaluation environment. View this score in rankings Accuracy 73.3% Reported 73.3% · Unit % Published Unconfirmed
GPT-5.4 (xhigh) Settings The release article states evaluations use xhigh unless otherwise noted. Unknowns none recorded Tools Tool access not recorded Reasoning budget xhigh Framework not recorded Protocol ARC-AGI-2 Verified;未注明题数。 Conditions 当前官方页面;修订及具体披露日期未知。除明确 None 外,主表总体脚注为 xhigh;研究环境结果可能与上线产品略有差异。 View this score in rankings