BACKGROUND: Matrix-assisted laser desorption/ionization time-of-flight mass spectrometry (MALDI-TOF MS) allows rapid and accurate identification of clinical yeast isolates. In-tube formic acid/acetonitrile (FA/ACN) extraction is recommended prior to the analysis with MALDI Biotyper, but the direct on-plate FA extraction is simpler. We compared the Biotyper with the VITEK MS for the identification of various clinically relevant yeast species, focusing on the use of the FA extraction method. METHODS: We analyzed 309 clinical isolates of 42 yeast species (four common Candida species, Cryptococcus neoformans, and 37 uncommon yeast species) using the Biotyper and VITEK MS systems. FA extraction was used initially for all isolates. If ‘no identification' result was obtained following the initial FA extraction, these samples were then retested by using FA (both systems, additive FA) or FA/ACN (Biotyper only, additive FA/ACN) extraction. These results were compared with those obtained by sequence-based identification. RESULTS: Both systems correctly identified all 158 isolates of the four common Candida species after the initial FA extraction. The Biotyper correctly identified 8.7%, 30.4%, and 100% of 23 C. neoformans isolates after performing initial FA, additive FA, and FA/ACN extractions, respectively, while VITEK MS identified all C. neoformans isolates after the initial FA extraction. Both systems had comparable identification rates of 37 uncommon yeast species (128 isolates), following the initial FA (Biotyper, 74.2%; VITEK MS, 73.4%) or additive FA (Biotyper, 82.0%; VITEK MS, 73.4%). CONCLUSIONS: The identification rate of most common and uncommon yeast isolates is comparable between simple FA extraction/Biotyper method and VITEK MS methods, but FA/ACN extraction is necessary for C. neoformans identification by Biotyper.