# Spatial Competence Benchmark

arXiv: https://arxiv.org/abs/2604.09594 · HTML: https://mlsanity.com/paper/2604.09594/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 16 references that are in the map.
- First posted on arXiv 5 Mar 2026.

## Builds on (most cited first, 12 of 12)

- [Is A Picture Worth A Thousand Words? Delving Into Spatial Reasoning for Vision Language Models](https://mlsanity.com/paper/2406.14852/) (2024)
- [lmgame-Bench: How Good are LLMs at Playing Games?](https://mlsanity.com/paper/2505.15146/) (2025)
- [LEGO-Puzzles: How Good Are MLLMs at Multi-Step Spatial Reasoning?](https://mlsanity.com/paper/2503.19990/) (2025)
- [Unfolding Spatial Cognition: Evaluating Multimodal Models on Visual Simulations](https://mlsanity.com/paper/2506.04633/) (2025)
- [When Visualizing is the First Step to Reasoning: MIRA, a Benchmark for Visual Chain-of-Thought](https://mlsanity.com/paper/2511.02779/) (2025)
- [SpinBench: Perspective and Rotation as a Lens on Spatial Reasoning in VLMs](https://mlsanity.com/paper/2509.25390/) (2025)
- [FloorplanQA: A Benchmark for Spatial Reasoning in LLMs using Structured Representations](https://mlsanity.com/paper/2507.07644/) (2025)
- [Probing Mechanical Reasoning in Large Vision Language Models](https://mlsanity.com/paper/2410.00318/) (2024)
- [11Plus-Bench: Demystifying Multimodal LLM Spatial Reasoning with Cognitive-Inspired Analysis](https://mlsanity.com/paper/2508.20068/) (2025)
- [Can LLMs See Without Pixels? Benchmarking Spatial Intelligence from Textual Descriptions](https://mlsanity.com/paper/2601.03590/) (2026)
- [GamiBench: Evaluating Spatial Reasoning and 2D-to-3D Planning Capabilities of MLLMs with Origami Folding Tasks](https://mlsanity.com/paper/2512.22207/) (2025)
- [APEX: Empowering LLMs with Physics-Based Task Planning for Real-time Insight](https://mlsanity.com/paper/2505.13921/) (2025)

## Abstract (arXiv)

Spatial competence is the quality of maintaining a consistent internal representation of an environment and using it to infer discrete structure and plan actions under constraints. Prevailing spatial evaluations for large models are limited to probing isolated primitives through 3D transformations or visual question answering. We introduce the Spatial Competence Benchmark (SCBench), spanning three hierarchical capability buckets whose tasks require executable outputs verified by deterministic checkers or simulator-based evaluators. On SCBench, three frontier models exhibit monotonically decreasing accuracy up the capability ladder. Sweeping output-token caps shows that accuracy gains concentrate at low budgets and saturate quickly, and failures are dominated by locally plausible geometry that breaks global constraints. We release the task generators, verifiers, and visualisation tooling.