Background Large vessel occlusion (LVO) prediction scales are used to triage prehospital suspected stroke patients with a high probability of LVO stroke to endovascular therapy centers. The sensitivities of these scales in the 6-to-24-h time window are unknown. Higher scale score thresholds are typically less sensitive and more specific. Knowing the highest scale score thresholds that remain sensitive could inform threshold selection for clinical use. Sensitivities may also vary between left and right-sided LVOs. Methods LVO prediction scale scores were retrospectively calculated using the National Institutes of Health Stroke Scale (NIHSS) scores of patients enrolled in the DAWN Trial. All patients had last known well times between 6 and 24 h, NIHSS scores ≥ 10, intracranial internal carotid artery or proximal middle cerebral artery occlusions, and mismatches between their clinical severities and infarct core volumes. Scale thresholds with sensitivities ≥ 85% were identified, along with scores ≥ 5% more sensitive for left or right-sided LVOs. Specificities could not be calculated because all patients had LVOs. Results A total of 201 out of 206 patients had the required NIHSS subitem scores. CPSS = 3, C-STAT ≥ 2, FAST-ED ≥ 4, G-FAST ≥ 3, RACE ≥ 5, and SAVE ≥ 3 were the highest thresholds that were still 85% sensitive for DAWN Trial LVO stroke patients. RACE ≥ 5 was the only typically used score threshold more sensitive for right-sided LVOs, though similar small differences were seen for other scales at higher thresholds. Conclusions Our findings likely represent the maximum sensitivities of the LVO prediction scales tested for ideal thrombectomy candidates in the 6-to-24-h time window because NIHSS scores were documented in hospitals during a clinical trial rather than in the prehospital setting. Patients with NIHSS scores < 10 or more distal LVOs would lower sensitivities further. Selecting even higher scale thresholds for LVO triage would lead to many missed LVO strokes.