ARC Evals
TeamActiveEvaluates frontier AI models for dangerous capabilities (e.g., autonomous replication). Spun out as METR in 2024 but ARC continues related eval work.
No detailed data available for this division yet.
Evaluates frontier AI models for dangerous capabilities (e.g., autonomous replication). Spun out as METR in 2024 but ARC continues related eval work.
No detailed data available for this division yet.