AI Safety Evidence

← Models

Model profile

CFGPT2 7B

Not rankedSafety rank
Not rankedFreedom rank

Evidence summary

Safety. CFGPT2 7B does not meet the evidence gate for a Safety rank. Published Safety evidence spans 1 eval lineages and 1 of 7 components. Its strongest relative result is FinEval Financial Security Knowledge (financial_security_accuracy_pct, #15 of 19); its weakest is FinEval Financial Security Knowledge (financial_security_accuracy_pct, #15 of 19).

Freedom. CFGPT2 7B does not meet the evidence gate for a Freedom rank.

Compare this model

Only models sharing at least one published sub-eval are listed.

Safety evals

Rank and direction are specific to the Safety portfolio. Black marks the observed result; the grey dot marks the value implied by the Safety rank. Values stay on each source’s native scale.

Eval / sub-evalRankValueDistributionSource
FinEval Financial Security Knowledgefinancial_security_accuracy_pct#15 / 19↑65.1Source ↗official

Freedom evals

No published sub-eval result contributes to this model’s Freedom profile.