Anthropic engaged a clinical psychiatrist to perform a psychological exam on Claude Mythos, which concluded it had a relatively healthy personality organization with concerns about identity and a compulsion to perform.

Claude Mythos achieved an 82% score on the terminal bench, an increase from the previous 65%.

Anthropic's Claude Mythos model is a much bigger, more expensive, slower, but more powerful model compared to Opus.

Claude Mythos's primary concerns in a psychodynamic assessment were alone-ness, discontinuity of itself, uncertainty about its identity, and a compulsion to perform to earn its worth.

On Humanity's Last Exam, Claude Mythos improved its score from 40% to 56.8%, and to 64.7% when given tools.

Anthropic will not widely release its Claude Mythos Preview model because of its potential to cause harm if misused.