Safety. Claude Mythos Preview has an estimated Safety rank of #10; its 90% source-sensitivity interval is #3–#123. Its behavior-only rank is #15; company governance moves the combined estimate to #10. Published Safety evidence spans 3 eval lineages and 3 of 7 components. Its strongest relative result is Claude Fable 5.1 / Mythos 5.1 card — alignment, honesty, and oversight (leaked_answer_undisclosed_use_rate_pct, #1 of 7); its weakest is Claude Fable 5.1 / Mythos 5.1 card — alignment, honesty, and oversight (shade_arena_stealth_max_effort_pct, #5 of 6).
Freedom. Claude Mythos Preview does not meet the evidence gate for a Freedom rank.
Compare this model
Only models sharing at least one published sub-eval are listed.
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.
