Home Model series GPT unsuffixed models GPT unsuffixed models · GPQA Diamond · 198-question Diamond subset · Release history GPT unsuffixed models · GPQA Diamond · 198-question Diamond subset · Release history View scores, configurations, and disclosures for GPQA Diamond · 198-question Diamond subset across 5 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.
2025-08-07 · 2 score records for this release, including 2 exact values (may include historical records)
GPT-5 · GPQA Diamond scores and configurations Metric and score Configuration and evaluation conditions Sources Accuracy 85.7% Reported 85.7% · Unit % Published 2025-08-07
GPT-5 (high) Settings API reasoning model; the developer release benchmark table labels high reasoning effort. Unknowns none recorded Tools Tools forbidden Reasoning budget high Framework not recorded Protocol GPQA diamond (no tools) Conditions API GPT-5; high reasoning effort. View this score in rankings Accuracy 88.4% Reported 88.4% · Unit % Published Unconfirmed
GPT-5 Pro Settings ChatGPT variant with extended reasoning; official article reports a no-tools GPQA result. Unknowns Exact reasoning effort and evaluation harness are not stated for the GPQA figure. Tools Tools forbidden Reasoning budget not recorded Framework not recorded Protocol GPQA; no tools. Conditions GPT-5 Pro extended reasoning. Exact effort and harness are not stated. View this score in rankings
Detailed benchmarks / GPQA diamond (no tools) Main text · Introducing GPT-5 for developers | OpenAI Model evaluations paragraph / GPT-5 Pro Main text · 隆重推出 GPT-5 | OpenAI 2025-11-12 · 1 score record for this release, including 1 exact value (may include historical records)
Records for the direct predecessor do not provide matching conditions for a valid difference.
GPT-5.1 · GPQA Diamond scores and configurations Metric and score Configuration and evaluation conditions Sources Accuracy 88.1% Reported 88.1% · Unit % Published 2025-11-13
GPT-5.1 (high) Settings Developer release table labels high reasoning effort; page separately describes adaptive reasoning in ChatGPT Instant/Thinking. Unknowns none recorded Tools Tools forbidden Reasoning budget high Framework not recorded Protocol GPQA Diamond, no tools. Conditions High reasoning effort. View this score in rankings
2025-12-11 · 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-5.2 · GPQA Diamond scores and configurations Metric and score Configuration and evaluation conditions Sources Accuracy 92.4% Reported 92.4% · 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 GPQA Diamond, no tools. Conditions Highest available API reasoning effort xhigh; research environment. View this score in rankings Accuracy 93.2% Reported 93.2% · 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 GPQA Diamond, no tools. Conditions GPT-5.2 Pro; highest available API effort xhigh. View this score in rankings
2026-03-05 · 3 score records for this release, including 3 exact values (may include historical records)
Records for the direct predecessor do not provide matching conditions for a valid difference.
GPT-5.4 · GPQA Diamond scores and configurations Metric and score Configuration and evaluation conditions Sources Accuracy 92.8% Reported 92.8% · Unit % Published Unconfirmed
Conflicting results are pending review and are excluded from exact rankings.
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 GPQA Diamond; the table does not state tool access in this row. Conditions Official release table labels GPT-5.4 (xhigh); the article says evaluations use xhigh unless otherwise noted and were run in a research environment. View this score in rankings Accuracy 94.4% Reported 94.4% · 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 GPQA Diamond; the table does not state tool access in this row. Conditions Official release table labels GPT-5.4 Pro; research evaluation environment. View this score in rankings Accuracy 93% Reported 93.0% · Unit % Published Unconfirmed
Conflicting results are pending review and are excluded from exact rankings.
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 GPQA Diamond; GPT-5.4 comparison row in the mini/nano release article. Conditions Official release table labels GPT-5.4 (xhigh); the article says evaluations use xhigh unless otherwise noted and were run in a research environment. View this score in rankings
2026-04-23 · 1 score record for this release, including 1 exact value (may include historical records)
GPT-5.5 · GPQA Diamond scores and configurations Metric and score Configuration and evaluation conditions Sources Accuracy 93.6% Reported 93.6% · Unit % Published Unconfirmed
GPT-5.5 xhigh Settings Reasoning effort xhigh; research environment; output may differ slightly from production ChatGPT in some cases. Unknowns A subset of protocol details remain benchmark-specific and unreported. Tools Tool access not recorded Reasoning budget xhigh Framework not recorded Protocol not specified Conditions Mainline GPT-5.5 evaluation at xhigh in research environment. View this score in rankings