Launching today
ATLAS
Benchmark
2 followers
Benchmark
2 followers
ATLAS is grounded in the 2026 Google DeepMind paper "Measuring Progress Toward AGI: A Cognitive Framework" (Burnell et al.), which identifies Learning as one of 10 core cognitive faculties and decomposes it into six sub-types. Where most benchmarks test knowledge retrieved from training data, ATLAS uses procedurally generated interactive environments where the model must discover hidden rules through trial-and-error in real time. No answer can be looked up. Every game is a new learning problem.
