Vision-Language-Action (VLA) models are advancing faster than the field can evaluate them reliably. Researchers use different metrics and lab-specific protocols, making it hard to tell whether reported gains reflect genuine progress or favorable evaluation choices. We present the first comprehensive benchmark-centric survey of VLA evaluation, covering 582 papers from 2023 to May 2026. We argue that a benchmark number supports a progress claim only if four conditions hold: the benchmark discriminates among top models; metrics capture the claimed capability; the procedure permits cross-paper comparison; and the inference from benchmark to deployment is valid. Current practice fails at all four. Benchmark choice is concentrated and saturated, with leading models clustering near the ceiling of dominant simulation suites. Metric reporting is one-dimensional, dominated by task success rate while efficiency, safety, and trajectory consistency remain underreported. Real-world evaluation is fragmented, with no widely adopted standard and few trials per task. Simulation scores are widely treated as evidence of real-world capability, yet standard task-centric suites correlate only weakly with real-robot performance unless explicitly calibrated to the target physical setup. These failures reveal a fundamental evaluation bottleneck: VLA models are advancing faster than our ability to measure that advance.

Spatial intelligence requires agents to form and utilize internal representations of the physical world for perception, reasoning, and generation. While recent advances in foundation models, embodied systems, and three-dimensional representation learning have substantially expanded spatial capabilities, existing research remains fragmented across heterogeneous tasks and model paradigms. This survey revisits spatial intelligence from a cognitive map perspective and positions cognitive maps as its representational blueprint. In this view, diverse lines of research can be understood through a shared question: how an internal spatial representation is constructed, maintained, reasoned over, and realized. To make this perspective operational, we define cognitive maps as internal spatial representations characterized by abstraction, globality, and persistency. Based on this definition, we organize the literature into three cognitive-map-centric processes that correspond to the core dimensions of spatial intelligence: perception for cognitive map construction, reasoning for internal inference with the map, and generation for external realization of the map. By adopting a mechanism-centric viewpoint, this survey connects previously isolated research directions into a coherent framework and identifies emerging challenges toward unified spatial intelligence systems. The related resources of this study are accessible at https://github.com/Klingsor-tyx/Awesome-Spatial-Cognitive-Map.