BACKGROUND: There are limited data about Xpert-Ultra performance in different settings, in HIV-infected persons, in those with a history of previous TB, and with trace readouts. METHODS: We evaluated the relative accuracy of Xpert-MTB/RIF and Xpert-Ultra in 272 selected but well-characterized archived sputum samples. Of these, 168 were culture-positive (64/168 smear-positive and 104/168 smear-negative), and 104 were culture-negative (102/104 from patients with previous TB and 2/104 from patients without a TB history). Assay-specific limit-of-detection (LOD) experiments were conducted using serial dilutions of Mycobacterium tuberculosis H37Rv. RESULTS: Overall sensitivity (95%CI) in smear-negative culture-positive samples for Xpert-MTB/RIF and Xpert-Ultra were 71.2% (62.5-79.9) and 77% (68.9-85.1), respectively (and in HIV-infected persons: 63.5% (50-76.1) and 73.1% (61.1-85.2), respectively). The LOD for Xpert-Ultra was lower (9 versus 184 CFU/ml). There were a total of 9/272 (3.3%) Xpert Ultra trace readouts (6/104 [5.8%]) in smear-negative culture-positive persons, and 3/102 (3%) in culture-negative non-TB persons with a history of previous TB). CONCLUSIONS: Xpert-Ultra had a lower LOD compared to Xpert-MTB/RIF. A small proportion of samples (<5%) from culture-negative patients but with a history of previous TB had a likely false-positive trace readout. These data inform the management of patients with suspected TB in endemic settings.