Understanding how functional traits affect plant performance and fitness is a key step in unravelling the role of natural selection in shaping the evolutionary trajectory of populations. We examined early-age selection acting on leaf traits via their effects on growth performance and fitness, measured in Eucalyptus ovata trees planted in a common-garden field trial embedded in a reforestation planting in Tasmania, Australia. We focused on two important leaf traits - stomatal length and specific leaf area (SLA) - measured two years after planting, and compared interplanted E. ovata groups originating from dry and wet home-site climates, with the trial site having intermediate long-term mean annual rainfall. Two-year height growth was used as the performance attribute, and the time-averaged tree survival over the subsequent six years as the fitness component. There was evidence for performance-based selection on the leaf traits, with the strength and form of selection depending on the trait and climate group being considered. In this sense, selection in the dry group operated mainly on stomatal length where a combination of directional (favouring longer stomata) and stabilizing selection was detected, whereas selection in the wet group acted only on SLA and was purely stabilizing. Estimates of performance-based correlational selection were not statistically significant. For both climate groups, estimates of fitness-based selection gradients provided evidence for significant directional (but not quadratic) selection on height performance, favouring individuals with faster growth, but did not indicate statistical support for direct effects of the leaf traits on tree survival, conditional on measured performance. These results validated qualitative inferences of selection from the performance-based analysis, and suggested that selection on the leaf traits appeared to be mediated by their effects on early-age height performance, which in turn directly influenced later-age survival. We discuss the mechanisms by which the focal traits may have affected height performance, and likely factors contributing to the different patterns of phenotypic selection observed in the two groups experiencing the same environment. We also provide expressions of analytical derivatives that were developed for the estimation of selection gradients based on a logistic regression model relating a binary fitness response to linear and nonlinear covariate terms for the target regressor variables.