Fetching from the wire…
01
02
03
04
05
06
07
08
Research2026-04-30 · source-backed
BioMysteryBench is a 99-question benchmark built from real bioinformatics datasets. Claude Mythos Preview cracked 30% of the 23 problems an expert panel gave up on, while Sonnet 4.6 performs on par with experts overall. The catch: 44% of Mythos's hardest-problem wins are "brittle," reproducing in fewer than 2 of 5 attempts. Lucky guesses, not reliable strategies. Promising but not dependable yet.
Each link below shares sources, entities, or timing with this story.
Anthropic released Mythos / Shared entities / Shared topic / What happened next
Linked by a graph relationship (Anthropic released Mythos); both cover Claude, Claude Mythos, Claude Mythos Preview, Mythos; overlapping topics (claude, mytho).
Anthropic released Mythos / Shared entities / Same source domain / Shared topic / What happened next
Linked by a graph relationship (Anthropic released Mythos); both cover CLAUDE, Mythos; reported by the same outlet (anthropic.com).
Anthropic released Mythos / Shared entities / Shared topic / What happened next / Tension
Linked by a graph relationship (Anthropic released Mythos); both cover CLAUDE, Sonnet; overlapping topics (anthropic, catch, claude).
Anthropic released Mythos / Shared entities / Same source domain / Shared topic / What happened next
Linked by a graph relationship (Anthropic released Mythos); both cover Claude, Mythos; reported by the same outlet (anthropic.com).
Linked by a graph relationship (Anthropic released Mythos); both cover CLAUDE, Claude Mythos; reported by the same outlet (anthropic.com).
Linked by a graph relationship (Anthropic released Mythos); both cover Claude, Mythos; reported by the same outlet (anthropic.com).
Anthropic released Mythos / Shared entities / Shared topic / What happened next / Tension
Linked by a graph relationship (Anthropic released Mythos); both cover Claude, Sonnet; overlapping topics (anthropic, claude).
Anthropic released Mythos / Shared entity: Claude / Same source domain / Shared topic / What happened next
Linked by a graph relationship (Anthropic released Mythos); both cover Claude; reported by the same outlet (anthropic.com).