Add safeagents judge bench results
#3
by adaamko - opened
our safeagents judge bench v0 run, test split, unmodified benchmark runner, fixed 0.5 cut-off, no tuning. revision 52ba9e7a0040
balanced accuracy 0.756, AUROC 0.994, false-block rate 0.487, category macro F1 0.491
Xunzhuo changed pull request status to merged
