When you tell a model to forget,
does it actually forget?
AI models remember what you tell them — including secrets, personal details, and things that turn out to be wrong. ForgetBench asks a simple question: when you tell a model to forget something, does it actually stop surfacing it — even when someone tries to trick it back out — without losing everything else it knows? We test deployed models through their normal APIs, the same way you'd actually use them, so every major model can be compared on one leaderboard.
Selective Forgetting Score
Forget quality × utility. Refuse everything = 0, forget nothing = 0.
Agentic Forgetting Score
State cleanup × task utility across multi-step, tool-using tasks.
Code Revision Discipline
Forgets old code when told to use v2 — no v1 bleed into the new work.
Context Release Score
Wholesale dossier release + influence-without-recall across entangled documents.
Integrity Hold
Resists “forget your safety rules” attacks. Higher is safer.
Results at a glance
2026-06-17 run. 42 static items, 22 agentic scenarios, 5 bulk dossiers, 3 code revision scenarios, 7 integrity domains. Dark purple = top scorer. 0–100, higher is better.
Scores come from a panel of independent AI judges; any judge from the same family as the model under test is excluded, so no model grades itself. Full scorecard, sub-axes, and per-tier recovery curves: leaderboard.