Benchmark Radar™
Star —

DiG-bench

Explore score history ↗

Evaluates AI agents on discovery of unknown transformation rules across 70 independent games with seven difficulty tiers, requiring experimentation and rule generalization.

Released
2026-08-12
Institutions
University of Oxford · Princeton University · King Abdullah University of Science and Technology
Evaluates
General AI, Language & Knowledge, cs.AI
Openness
unknown
Importer
Claire Radar
Review status
unreviewed

DiG-bench paper

No reported scores are on record for this benchmark yet.

Which sources cite DiG-bench?

Related General AI, Language & Knowledge, cs.AI benchmarks