This paper presents a comparison between three different modes of simulation of the diagnostic process-a computer-based system, a verbal mode, and a further mode in which cards were selected from a large board. A total of 34 subjects worked through a series of 444 diagnostic simulations.The verbal mode was found to be most enjoyable and realistic. At the board, considerable amounts of extra irrelevant data were selected. At the computer, the users asked the same questions every time, whether or not they were relevant to the particular diagnosis. They also found the teletype distracting, noisy, and slow.The need for an acceptable simulation system remains, and at present our Minisim and verbal modes are proving useful in training junior clinical students. Future simulators should be flexible, economical, and acceptably realistic-and to us this latter criterion implies the two-way use of speech. We are currently developing and testing such a system.