Home Model series GPT Sol GPT-6.2 Sol GPT-6.2 Sol · Harvey LAB-AA · Artificial Analysis v1.1; 120-task held-out set; hallucination-gated and ungated all-pass rates · Scores and configurations GPT-6.2 Sol · Harvey LAB-AA · Artificial Analysis v1.1; 120-task held-out set; hallucination-gated and ungated all-pass rates · Scores and configurations GPT-6.2 Sol record for Harvey LAB-AA · Artificial Analysis v1.1; 120-task held-out set; hallucination-gated and ungated all-pass rates. 5 score records for this release, including 5 exact values (may include historical records). Includes 5 source locations.
Scores and evaluation conditions GPT-6.2 Sol · Harvey LAB-AA scores and configurations Metric and score Configuration and evaluation conditions Sources Hallucination-gated all-pass rate 3.1% Reported 3.1% · Unit % Published Unconfirmed
GPT-6.2 Sol low Settings GPT-6.2 Sol; reasoning effort low, explicitly labeled in the official chart data. Unknowns 文章未注明逐项采样设置、完整执行框架和工具配置;按图表所示条件记录。 Tools Tool access not recorded Reasoning budget low Framework not recorded Protocol not specified Conditions GPT-6.2 Sol; reasoning effort low. 仅当交付物满足全部标准且无实质性幻觉时计分。 官方图表单任务成本:$0.25。逐项采样及完整 harness 未注明。 View this score in rankings Hallucination-gated all-pass rate 5% Reported 5.0% · Unit % Published Unconfirmed
GPT-6.2 Sol medium Settings GPT-6.2 Sol; reasoning effort medium, explicitly labeled in the official chart data. Unknowns 文章未注明逐项采样设置、完整执行框架和工具配置;按图表所示条件记录。 Tools Tool access not recorded Reasoning budget medium Framework not recorded Protocol not specified Conditions GPT-6.2 Sol; reasoning effort medium. 仅当交付物满足全部标准且无实质性幻觉时计分。 官方图表单任务成本:$0.71。逐项采样及完整 harness 未注明。 View this score in rankings Hallucination-gated all-pass rate 5.8% Reported 5.8% · Unit % Published Unconfirmed
GPT-6.2 Sol high Settings GPT-6.2 Sol; reasoning effort high, explicitly labeled in the official chart data. Unknowns 文章未注明逐项采样设置、完整执行框架和工具配置;按图表所示条件记录。 Tools Tool access not recorded Reasoning budget high Framework not recorded Protocol not specified Conditions GPT-6.2 Sol; reasoning effort high. 仅当交付物满足全部标准且无实质性幻觉时计分。 官方图表单任务成本:$1.03。逐项采样及完整 harness 未注明。 View this score in rankings Hallucination-gated all-pass rate 6.1% Reported 6.1% · Unit % Published Unconfirmed
GPT-6.2 Sol xhigh Settings GPT-6.2 Sol; reasoning effort xhigh, explicitly labeled in the official chart data. Unknowns 文章未注明逐项采样设置、完整执行框架和工具配置;按图表所示条件记录。 Tools Tool access not recorded Reasoning budget xhigh Framework not recorded Protocol not specified Conditions GPT-6.2 Sol; reasoning effort xhigh. 仅当交付物满足全部标准且无实质性幻觉时计分。 官方图表单任务成本:$1.23。逐项采样及完整 harness 未注明。 View this score in rankings Hallucination-gated all-pass rate 11.1% Reported 11.1% · Unit % Published Unconfirmed
GPT-6.2 Sol max Settings GPT-6.2 Sol; reasoning effort max, explicitly labeled in the official chart data. Unknowns 文章未注明逐项采样设置、完整执行框架和工具配置;按图表所示条件记录。 Tools Tool access not recorded Reasoning budget max Framework not recorded Protocol not specified Conditions GPT-6.2 Sol; reasoning effort max. 仅当交付物满足全部标准且无实质性幻觉时计分。 官方图表单任务成本:$1.92。逐项采样及完整 harness 未注明。 View this score in rankings
Benchmark versions and metrics Aliases Harvey LAB-AA v1.1
Hallucination-gated all-pass rate · % · Higher is better All-pass rate before hallucination gate · % · Higher is better