This study focuses on developing a five-tier chemical diagnostic test based on a computer-based test with 11 assessment categories with an assessment score from 0 to 10. A total of 20 items produced were validated by education experts, material experts, measurement experts, and media experts, and an average index of the Aiken test > 0.70 was obtained. The validation results were tested on 580 respondents and analyzed using the Generalized Partial Credit Model (GPCM) Item Response Theory (IRT) type. The results of the analysis show that all of the items meet the requirements to be said to be valid for the model; the evidence of the value this: RMSEA < 0.08, CFI > 0.87, SRMR < 0.10, GFI > 0.90, NFI > 0.90, NNFI > 0.90, IFI > 0.90, TLI > 0.90, and RFI > 0.90, and all items were obtained has a p.S_X2 value greater than 0.05 which indicates that all items developed are fit and by the GPCM model. The construct reliability (CR) value is 0.99, which suggests the construct is reliable. The most challenging item is item 9, and the most accessible item is item 4. [Note: The page range (91-105) shown on the PDF citation is incorrect. The correct page range is 92-106.]