Large cross-laminated timber (CLT) floors are inevitably composed of multiple CLT panels assembled on the construction site. Due to the sheer lack of adequate numerical characterization of the inter-panel connections, CLT floors are normally modelled as monolithic structures or independent “piano keyboards”, yielding errors between simulated and the actual vibration response. This paper presents a benchmark study for a deterministic finite element (FE) model updating of so called “an equivalent elastic strip” representation of the inter-panel connections. Fitting modelling parameters of the strip, i.e. its width and material properties, featured FE modelling and modal testing of two full-scale CLT floors composed of one and two panels connected with a half-lapped joint. The floors were made of (almost) identical panels and placed on elastic mats along their shorter edges. First, the single-panel floor was used to fit material properties of the timber and the boundary conditions. Then, the FE model updating (FEMU) of two-panel floor yielded the actual values of the strip modelling parameters. Finally, these were successfully verified by direct comparison between numerically calculated and experimentally measured modal properties of a full-scale model of a simply supported three-panel floor. The results implied that the rotational stiffness of the inter-panel connection depends strongly on its vertical vibration displacement. Consequently, values of the rotational stiffness derived from rare static tests published so far cannot be used reliably in a much subtler vibration response analysis. Future studies should feature other types of the inter-panel connections in various floor layouts and a probabilistic FEMU.