Table 13 reports Qwen3-30B-A3B-Instruct scores on nine likelihood-scored text QA datasets for every FIXED-K budget from k=8 to k=1.

Table 13 reports Qwen3-30B-A3B-Instruct scores on nine likelihood-scored text QA datasets for every FIXED-K budget from k=8 to k=1. · CiteArk

已评估 0/80 项

获得支持 0有争议或冲突 0尚未评估 80

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: 60.8	60.8 percentage points	—	尚未评估
printedValue: 85.0	85 percentage points	—	尚未评估
printedValue: 73.2	73.2 percentage points	—	尚未评估
printedValue: 32.0	32 percentage points	—	尚未评估
printedValue: 88.7	88.7 percentage points	—	尚未评估
printedValue: 80.1	80.1 percentage points	—	尚未评估
printedValue: 54.1	54.1 percentage points	—	尚未评估
printedValue: 80.1	80.1 percentage points	—	尚未评估
printedValue: 61.2	61.2 percentage points	—	尚未评估
printedValue: 68.36	68.36 percentage points	—	尚未评估
printedValue: 60.3	60.3 percentage points	—	尚未评估
printedValue: 84.0	84 percentage points	—	尚未评估

报告指标与观测值