The present study aimed to compare health outcomes and tolerability according to antipsychotic medication (olanzapine, risperidone or an oral typical antipsychotic) after 6 months of treatment in a group of 919 schizophrenic patients who had never previously been treated with antipsychotics. Demographic and clinical predictors of outcome were also identified. Data were extracted from the Schizophrenia Outpatient Health Outcomes (SOHO) study, a prospective, observational study of schizophrenia treatment in 10 European countries. Patients who initiated olanzapine were more likely to have a clinical response than those in the risperidone cohort, and had a greater improvement in quality of life than patients in the risperidone or typical antipsychotic cohorts. High negative and depression symptom scores at baseline and the presence of extrapyramidal symptoms at baseline predicted a worse clinical response, whereas hostile behaviour, paid employment and substance abuse predicted a better clinical outcome. The olanzapine cohort gained more weight than patients in the risperidone cohort, but no significant difference in weight gain was observed between olanzapine and the oral typical antipsychotic cohort. The results should be interpreted conservatively due to the observational study design.