Share this page

DoomBench social sharing card for Defense Llama.
  1. Defense Llama by Scale AI has a DoomBench model risk score of 37.4 out of 100, based on five transparent version-specific dimensions rather than the overall index.

  2. Defense Llama's highest current DoomBench dimension is misuse potential at 72.0 out of 100; the profile publishes every component score and its editorial rationale.

  3. DoomBench links 1 source-backed evidence item to Defense Llama, while keeping the model's risk profile separate from each item's contribution to the live Doom Index.

    https://www.doombench.com/models/scale-ai-defense-llama