AI Hub
All models

AlphaZero

DeepMind

Updated May 21, 2026 · Benchmarks via Artificial Analysis, specs & pricing via OpenRouter · Methodology · Report an error

Specifications

Released
December 5, 2017

Our take

Mastered chess, shogi, and Go from scratch through self-play alone, with no human game data — a striking demonstration of general reinforcement learning.

Related research

Compare AlphaZero with

See all AlphaZero alternatives →