The usefulness of dogs and monkeys in predicting potential qualitative drug toxicity in man was examined retrospectively for twenty‐five anticancer compounds of diverse chemical and functional classification. It was found that the large animal screen served to alert the physician to a significant proportion of the total spectrum of drug effects, which were encountered during the clinical use of a new toxic compound. The dog and monkey correctly predicted bone marrow depression, gastrointestinal disturbance, and hepatotoxicity for each drug producing these effects in the clinic; in the case of renal, cardiovascular, and neuromuscular toxicity, however, the large animal screen failed in each instance to predict one drug that produced these toxicities in man. The correct predictions were accomplished at the expense of a high percentage of false positives, which resulted from the necessity of using severely toxic dose levels in order to demonstrate all potential toxicities inherent in any compound. While organ system toxicity observed during an animal study can never be disregarded, it should be viewed with an understanding of certain limitations of animal toxicologic data. While toxicity may develop in man in an organ system predicted susceptible by an animal, a different specific clinical or chemical parameter may be involved. The adverse reaction may appear in man at a greater or lesser dose level or may follow a different order of appearance in relationship to the total spectrum of qualitative toxicity inherent in the compound.