AGC-Bench: Measuring Artificial General Creativity
Creativity research has debated whether creativity is domain-specific (e.g., visual, writing, science), and if it is psychometrically separable from general intelligence. Both questions now apply to LLMs, but a unified benchmark of AI creativity remains elusive. We introduce AGC-Bench, an artificial general creativity benchmark built from a systematic review of the AI creativity literature (3,101 papers screened, 497 benchmarks identified), paired with an agentic harness that converts idiosyncratic codebases into HELM-standardized benchmarks. The first release covers 78 datasets spanning brain
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
- Linked via arxiv authorRoger Beaty →
AGC-Bench: Measuring Artificial General Creativity
- Linked via arxiv authorVijeta Deshpande →
AGC-Bench: Measuring Artificial General Creativity
- Linked via arxiv authorClin K. Y. Lai →
AGC-Bench: Measuring Artificial General Creativity
- Linked via arxiv authorAnna Attuch →
AGC-Bench: Measuring Artificial General Creativity
- Linked via arxiv authorNamrata Shivagunde →
AGC-Bench: Measuring Artificial General Creativity
- Linked via arxiv authorSwastik Roy →
AGC-Bench: Measuring Artificial General Creativity
- Linked via arxiv authorRajkumar Pujari →
AGC-Bench: Measuring Artificial General Creativity
- Linked via arxiv authorPaul V. DiStefano →
AGC-Bench: Measuring Artificial General Creativity
- Linked via arxiv authorSherin Muckatira →
AGC-Bench: Measuring Artificial General Creativity
- Linked via arxiv authorClaire E. Stevenson →
AGC-Bench: Measuring Artificial General Creativity
- Linked via arxiv authorMikhail Gronas →
AGC-Bench: Measuring Artificial General Creativity
- Linked via arxiv authorAnna Rumshisky →
AGC-Bench: Measuring Artificial General Creativity