Alternating-current (AC) driven light-emitting diodes (LEDs) have become the trend of solid-state lighting (SSL) products. The junction temperature is an important index of LEDs reliability and efficiency. In other words, with proper thermal management of AC LEDs lighting products, the high performance of SSL products will be achieved. In order to obtain the junction temperature, we study and compare two published evaluating methods differentiating between the measurements of DC and AC in this paper. The first method is in which a low reference current having a pulse width was applied and the corresponding voltage across the device was measured and correlated to the junction temperature (Tj). The second method is using an active heat sink for recovering the root mean square (RMS) current of the first half cycle to estimate the junction temperature. The experimental evidence showed different aspects and variations of evaluating the AC LEDs junction temperature. The variations of evaluating junction temperature were caused by the switch time and phase of different source measurements in the first method and the capture time of the first half cycle in the second method. With proper capture time, the rising junction temperature in the second method might be negligible.