We conduct a laboratory experiment with a constant-sum sender–receiver game and a sequential game of matching pennies with the same payoff structure to investigate the impact of individuals’ first- and second-order beliefs on truth-telling. While first-movers in matching pennies choose an action at random, senders in the sender–receiver game tell the truth more often than they lie. Since second-order beliefs are uncorrelated with actions in both games, excessive truth-telling is unlikely to be driven by guilt aversion or preferences for truth-telling that are based on second-order beliefs; preferences for truth-telling per-se, on the other hand, cannot be rejected.