Although the scientific community increasingly recognizes that its communication with the public may shape civic engagement with science, few studies have characterized how this communication occurs online. Social media plays a growing role in this engagement, yet it is not known if or how different platforms support different types of engagement. This study sets out to explore how users engage with science communication items on different platforms of social media, and what are the characteristics of the items that tend to attract large numbers of user interactions. Here, user interactions with almost identical items on five of CERN's social media platforms were quantitatively compared over an eight-week period, including likes, comments, shares, click-throughs, and time spent on CERN's site. The most popular items were qualitatively analyzed for content features. Findings indicate that as audience size of a social media platform grows, the total rate of engagement with content tends to grow as well. However, per user, engagement tends to decline with audience size. Across all platforms, similar topics tend to consistently receive high engagement. In particular, awe-inspiring imagery tends to frequently attract high engagement across platforms, independent of newsworthiness. To our knowledge, this study provides the first cross-platform characterization of public engagement with science on social media. Findings, although focused on particle physics, have a multidisciplinary nature; they may serve to benchmark social media analytics for assessing science communication activities in various domains. Evidence-based suggestions for practitioners are also offered.