SpatialBench: Can Agents Analyze Real-World Spatial Biology Data?

TL;DR

SpatialBench is a comprehensive benchmark designed to evaluate AI agents' ability to analyze complex, real-world spatial transcriptomics data, highlighting current limitations and guiding future improvements.

Contribution

The paper introduces SpatialBench, a benchmark with 146 problems for assessing AI agents' performance on practical spatial biology analysis tasks.

Findings

Base model accuracy remains low (20-38%) across models.

Model performance varies significantly with task, platform, and design choices.

Design elements like prompts and control flow greatly impact results.

Abstract

Spatial transcriptomics assays are rapidly increasing in scale and complexity, making computational analysis a major bottleneck in biological discovery. Although frontier AI agents have improved dramatically at software engineering and general data analysis, it remains unclear whether they can extract biological insight from messy, real-world spatial datasets. We introduce SpatialBench, a benchmark of 146 verifiable problems derived from practical spatial analysis workflows spanning five spatial technologies and seven task categories. Each problem provides a snapshot of experimental data immediately prior to an analysis step and a deterministic grader that evaluates recovery of a key biological result. Benchmark data on frontier models shows that base model accuracy remains low (20-38% across model families), with strong model-task and model-platform interactions. Harness design has a large empirical effect on performance, indicating that tools, prompts, control flow, and execution environment should be evaluated and improved as first-class objects. SpatialBench serves both as a measurement tool and a diagnostic lens for developing agents that can interact with real spatial datasets faithfully, transparently, and reproducibly.