GPT-6.2 Sol; reasoning effort max, explicitly labeled in the official chart data.
未知项
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。
工具
工具条件未记录
推理预算
max
框架
未记录
协议
Four independent responses per conversation; rubric score clipped to 0–100%; within-task mean then mean across 1,215 tasks.
条件
Maximum reasoning effort explicitly stated. 1,215 synthetic conversations with clinician-authored rubrics; overall score, standard error ±1.0 percentage point across task means. 不将non-acute/high-acuity/emergent子集或动态对抗式政策合规评测混为总体成绩。其他采样参数、工具和完整harness未注明。
GPT-6.2 Sol · MentalHealthBench · Overall; 1,215 synthetic conversations; four independent responses per task; clinician-authored rubrics · Scores and configurations
GPT-6.2 Sol record for MentalHealthBench · Overall; 1,215 synthetic conversations; four independent responses per task; clinician-authored rubrics. 1 score record for this release, including 1 exact value (may include historical records). Includes 1 source location.
GPT-6.2 Sol · MentalHealthBench scores and configurations
Metric and score
Configuration and evaluation conditions
Sources
Mean task-clipped score50.9%Reported 50.9% ± 1.0 · 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
Four independent responses per conversation; rubric score clipped to 0–100%; within-task mean then mean across 1,215 tasks.
Conditions
Maximum reasoning effort explicitly stated. 1,215 synthetic conversations with clinician-authored rubrics; overall score, standard error ±1.0 percentage point across task means. 不将non-acute/high-acuity/emergent子集或动态对抗式政策合规评测混为总体成绩。其他采样参数、工具和完整harness未注明。