Benchmark Radar™
Star —

RestoreBench

Explore score history ↗

RestoreBench evaluates LLM agents on restoring AC power-flow convergence through reactive-control maneuvers in non-convergent power-grid snapshots, with success determined by a physics solver and fixed budget.

Released
2026-08-31
Institutions
ETH Zurich · Politecnico di Milano · Harvard University
Evaluates
Agents, General AI, Language & Knowledge
Openness
unknown
Importer
Claire Radar
Review status
ai-reviewed

RestoreBench paper and code

No reported scores are on record for this benchmark yet.

Which sources cite RestoreBench?

Related Agents, General AI, Language & Knowledge benchmarks