Table 10 reports every evaluated rule at both conservative and aggressive budget tiers for GPT-OSS-20B, including per-dataset scores, measured budgets, and suite means.

Table 10 reports every evaluated rule at both conservative and aggressive budget tiers for GPT-OSS-20B, including per-dataset scores, measured budgets, and suite means. · CiteArk

测量结果

已评估 0/166 项

获得支持 0有争议或冲突 0尚未评估 166

保留同一结论下的完整结果组。已有评估排在前面；单项判断不替代整组结论。展开行查看条件、来源与历次证据。

每行是一项测量，分别显示论文报告、最近可用实测和累计证据状态。
指标与条件	论文报告	最近可用实测	证据判断
printedValue: 45.3	45.3 percentage points	—	尚未评估
printedValue: 77.5	77.5 percentage points	—	尚未评估
printedValue: 66.9	66.9 percentage points	—	尚未评估
printedValue: 27.2	27.2 percentage points	—	尚未评估
printedValue: 90.6	90.6 percentage points	—	尚未评估
printedValue: 73.7	73.7 percentage points	—	尚未评估
printedValue: 71.7	71.7 percentage points	—	尚未评估
printedValue: 86.2	86.2 percentage points	—	尚未评估
printedValue: 58.3	58.3 percentage points	—	尚未评估
printedValue: 74.3	74.3 percentage points	—	尚未评估
printedValue: 64.6	64.6 percentage points	—	尚未评估
printedValue: 66.94	66.94 percentage points	—	尚未评估

Table 10 reports every evaluated rule at both conservative and aggressive budget tiers for GPT-OSS-20B, including per-dataset scores, measured budgets, and suite means.

报告指标与观测值

Assessment（0）

关联运行（0）

测量结果