Home Model series GPT Luna GPT-5.6 Luna GPT-5.6 Luna · BrowseComp · 1,266 题;单代理与多代理按协议区分 · Scores and configurations GPT-5.6 Luna · BrowseComp · 1,266 题;单代理与多代理按协议区分 · Scores and configurations GPT-5.6 Luna record for BrowseComp · 1,266 题;单代理与多代理按协议区分. 6 score records for this release, including 6 exact values (may include historical records). Includes 6 source locations.
Scores and evaluation conditions GPT-5.6 Luna · BrowseComp scores and configurations Metric and score Configuration and evaluation conditions Sources Accuracy 83.3% Reported 83.3% · Unit % Published Unconfirmed
GPT-5.6 Luna · 档位未注明 Settings 主文表格未逐行标明本型号推理档位;不套用 Sol 的 effort,也不以价格推断档位。 Unknowns 推理档位、部分评测的完整 harness 与采样设置 Tools Tool access not recorded Reasoning budget not recorded Framework not recorded Protocol not specified Conditions GPT-5.6 Luna;主文同表主体列原值,未逐行标明 effort。行名与工具条件:BrowseComp。 View this score in rankings Accuracy 45.73% Reported 45.73% · Unit % Published Unconfirmed
GPT-5.6 Luna (low) Settings GPT-5.6 Luna; reasoning effort Low as directly labeled on the official chart. Unknowns Per-benchmark sampling and chart harness settings are not stated. Tools Tool access not recorded Reasoning budget Low Framework not recorded Protocol BrowseComp; chart score; task harness details are not stated in this figure. Conditions GPT-5.6 Luna; reasoning effort Low directly labeled by the chart. Chart x-axis API cost: $0.08. Other run settings are not stated. View this score in rankings Accuracy 58.85% Reported 58.85% · Unit % Published Unconfirmed
GPT-5.6 Luna (medium) Settings GPT-5.6 Luna; reasoning effort Medium as directly labeled on the official chart. Unknowns Per-benchmark sampling and chart harness settings are not stated. Tools Tool access not recorded Reasoning budget Medium Framework not recorded Protocol BrowseComp; chart score; task harness details are not stated in this figure. Conditions GPT-5.6 Luna; reasoning effort Medium directly labeled by the chart. Chart x-axis API cost: $0.23. Other run settings are not stated. View this score in rankings Accuracy 80.02% Reported 80.02% · Unit % Published Unconfirmed
GPT-5.6 Luna (high) Settings GPT-5.6 Luna; reasoning effort High as directly labeled on the official chart. Unknowns Per-benchmark sampling and chart harness settings are not stated. Tools Tool access not recorded Reasoning budget High Framework not recorded Protocol BrowseComp; chart score; task harness details are not stated in this figure. Conditions GPT-5.6 Luna; reasoning effort High directly labeled by the chart. Chart x-axis API cost: $1.03. Other run settings are not stated. View this score in rankings Accuracy 84.04% Reported 84.04% · Unit % Published Unconfirmed
GPT-5.6 Luna (xhigh) Settings GPT-5.6 Luna; reasoning effort Xhigh as directly labeled on the official chart. Unknowns Per-benchmark sampling and chart harness settings are not stated. Tools Tool access not recorded Reasoning budget Xhigh Framework not recorded Protocol BrowseComp; chart score; task harness details are not stated in this figure. Conditions GPT-5.6 Luna; reasoning effort Xhigh directly labeled by the chart. Chart x-axis API cost: $1.33. Other run settings are not stated. View this score in rankings Accuracy 83.25% Reported 83.25% · Unit % Published Unconfirmed
GPT-5.6 Luna (max) Settings GPT-5.6 Luna; reasoning effort Max as directly labeled on the official chart. Unknowns Per-benchmark sampling and chart harness settings are not stated. Tools Tool access not recorded Reasoning budget Max Framework not recorded Protocol BrowseComp; chart score; task harness details are not stated in this figure. Conditions GPT-5.6 Luna; reasoning effort Max directly labeled by the chart. Chart x-axis API cost: $1.42. Other run settings are not stated. View this score in rankings
Benchmark versions and metrics Aliases BrowseComp、Multi-agent BrowseComp
Accuracy · % · Higher is better