A 70-game interactive benchmark where agents must discover hidden rules and objectives, with human beatability on every game and frontier models failing on the hardest tiers.
How enabling two settings tripled our scores on the ARC-AGI-3 benchmark, July 2026
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
DiG-bench: Discovery in Games
A 70-game interactive benchmark where agents must discover hidden rules and objectives, with human beatability on every game and frontier models failing on the hardest tiers.