List your company

Cybersecurity Incident Response on 120-event corpus seed 42

58TP (True Positives)Agentra (M4)
619.53346.5Jun 16, 2026

Evaluation results

MethodLinks
Agentra (M4)Ablation Stage=A42026.06580273568100819073680
Agentra (M4)Ablation Stage=A32026.0656228346797799372680.9
Agentra (M5)Ablation Stage=A12026.06535243869917980312314.2
Agentra (M1)Ablation Stage=A42026.0652614487990844784840
Agentra (M4)Ablation Stage=A12026.06526293364907597371516
Agentra (M4)Ablation Stage=A22026.06526253768907783371517.5
Agentra (M1)Ablation Stage=A32026.06481013497983814379790
Agentra (M2)Ablation Stage=A42026.06382010527966723376760
Agentra (M3)Ablation Stage=A32026.06382013497566704372730
Agentra (M2)Ablation Stage=A32026.0636228548262712775750
Agentra (M5)Ablation Stage=A32026.0636229538062703096950
Agentra (M5)Ablation Stage=A42026.0633258548157672795950
CACAO baselineCombo=M1, Ablation Stage=A02026.06322615476855615037850
CACAO baselineCombo=M2, Ablation Stage=A02026.06322615476855615037850
Agentra (M2)Ablation Stage=A12026.063226174565556057243010.4
CACAO baselineCombo=M3, Ablation Stage=A02026.06322615476855615037850
Agentra (M3)Ablation Stage=A42026.06322612507355634077770
CACAO baselineCombo=M4, Ablation Stage=A02026.06322615476855615037850
CACAO baselineCombo=M5, Ablation Stage=A02026.06322615476855615037850
Agentra (M1)Ablation Stage=A12026.0629298547850612716224.3
Agentra (M1)Ablation Stage=A22026.0627316568247592017236.3
Agentra (M3)Ablation Stage=A12026.06233510527040513324305.4
Agentra (M3)Ablation Stage=A22026.06203813496134444323278.5
Agentra (M2)Ablation Stage=A22026.0617418546829412719262.2
Agentra (M5)Ablation Stage=A22026.068501618914243422033.3