Penelitian ini bertujuan untuk membandingkan tingkat akurasi setiap model prediksi financial distress (Grover, Springate, Taffler, Zmijewski, Altman ZScore) dari data selama Tax amnesty dan data setelah Tax amnesty dengan Interest Coverage Ratio (ICR) sebagai pengukuran financial distress. Analisis dilakukan dengan menggunakan 103 sampel perusahaan yang tercatat di Bursa Efek Indonesia (BEI) periode tahun 2016 sampai dengan tahun 2019. Hasil penelitian menunjukkan bahwa terdapat perbedaan signifikan tingkat akurasi setiap model baik dari data selama Tax amnesty maupun setelah Tax amnesty, serta dari kedua data tersebut menyatakan bahwa model prediksi yang memiliki tingkat akurasi tertinggi diperoleh oleh model Zmijewski. This study aims to compare the accuracy of each financial distress prediction model (Grover, Springate, Taffler, Zmijewski, Altman Z-Score) from data during the Tax amnesty and data after the Tax amnesty with the interest coverage ratio (ICR) as a measurement of financial distress. The analysis was carried out using 103 samples of companies listed on the Indonesia Stock Exchange (IDX) for the period 2016 to 2019. The results showed that there were significant differences in the level of accuracy of each model both from the data during the Tax amnesty and after the Tax amnesty, and from the two data it was stated that the prediction model that had the highest level of accuracy was obtained by the Zmijewski model.