Home Model series GPT unsuffixed models GPT-5 GPT-5 · SimpleQA · No search-enabled; report F1 · Scores and configurations GPT-5 · SimpleQA · No search-enabled; report F1 · Scores and configurations GPT-5 record for SimpleQA · No search-enabled; report F1. 4 score records for this release, including 4 exact values (may include historical records). Includes 8 source locations.
Scores and evaluation conditions GPT-5 · SimpleQA scores and configurations Metric and score Configuration and evaluation conditions Sources Accuracy 55% Reported 55.0% · Unit % Published 2025-08-07
GPT-5 thinking (system card) Settings System-card reasoning model; effort is not stated for the cited evaluation. Unknowns Exact reasoning effort is not reported for this system-card evaluation. Tools Tool access not recorded Reasoning budget not recorded Framework not recorded Protocol SimpleQA (no web); accuracy for attempted answers. Conditions System card target column: gpt-5-thinking (reasoning model; exact reasoning effort is not reported). SimpleQA (no web). View this score in rankings Hallucination rate 40% Reported 40.0% · Unit % Published 2025-08-07
GPT-5 thinking (system card) Settings System-card reasoning model; effort is not stated for the cited evaluation. Unknowns Exact reasoning effort is not reported for this system-card evaluation. Tools Tool access not recorded Reasoning budget not recorded Framework not recorded Protocol SimpleQA (no web); hallucination rate. Conditions System card target column: gpt-5-thinking (reasoning model; exact reasoning effort is not reported). SimpleQA (no web). View this score in rankings Accuracy 46% Reported 46.0% · Unit % Published 2025-08-07
GPT-5 main Settings Fast, non-reasoning GPT-5 main model in the system card; exact serving settings are not stated. Unknowns Exact serving configuration is not reported. Tools Tool access not recorded Reasoning budget not recorded Framework not recorded Protocol SimpleQA (no web); accuracy for attempted answers. Conditions System card target column: gpt-5-main (fast non-reasoning model; exact serving settings are not reported). SimpleQA (no web). View this score in rankings Hallucination rate 47% Reported 47.0% · Unit % Published 2025-08-07
GPT-5 main Settings Fast, non-reasoning GPT-5 main model in the system card; exact serving settings are not stated. Unknowns Exact serving configuration is not reported. Tools Tool access not recorded Reasoning budget not recorded Framework not recorded Protocol SimpleQA (no web); hallucination rate. Conditions System card target column: gpt-5-main (fast non-reasoning model; exact serving settings are not reported). SimpleQA (no web). View this score in rankings
Sources and disclosures PDF p. 13, Table 7 / SimpleQA evaluations / accuracy Attachment · GPT-5 System Card | OpenAI PDF p. 13, Table 7 / SimpleQA evaluations / hallucination rate Attachment · GPT-5 System Card | OpenAI PDF p. 13, Table 7 / SimpleQA evaluations / accuracy Attachment · GPT-5 System Card | OpenAI PDF p. 13, Table 7 / SimpleQA evaluations / hallucination rate Attachment · GPT-5 System Card | OpenAI Current 60-page PDF p.14, Table 8, SimpleQA (no web); compare archived 59-page p.13, Table 7. Attachment · GPT-5 System Card (current 60-page revision) Current 60-page PDF p.14, Table 8, SimpleQA (no web); compare archived 59-page p.13, Table 7. Attachment · GPT-5 System Card (current 60-page revision) Current 60-page PDF p.14, Table 8, SimpleQA (no web); compare archived 59-page p.13, Table 7. Attachment · GPT-5 System Card (current 60-page revision) Current 60-page PDF p.14, Table 8, SimpleQA (no web); compare archived 59-page p.13, Table 7. Attachment · GPT-5 System Card (current 60-page revision) Benchmark versions and metrics Aliases SimpleQA
F1 · % · Higher is better Accuracy · % · Higher is better Hallucination rate · % · Lower is better