Acropolis

davinci-002

OpenAIGrade C. Evidence grade C of A to D: thin.Weights unstated
Compare with peers

Benchmark appearances

Best verified run per board, with confidence intervals and Pareto frontier status.

BenchmarkRankScoreCostStatusObserved
METR time horizon

METR time horizons · modular-public

#2 / 3
0.1 min[0.1 min to 0.2 min]UnknownStandardNot stated