# Verifiable Benchmarking of Long-Horizon Spatial Biology

arXiv: https://arxiv.org/abs/2605.28065 · HTML: https://mlsanity.com/paper/2605.28065/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 32 references that are in the map.
- First posted on arXiv 27 May 2026.

## Builds on (most cited first, 6 of 6)

- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Let's Verify Step by Step](https://mlsanity.com/paper/2305.20050/) (2023)
- [Large Language Models are not Fair Evaluators](https://mlsanity.com/paper/2305.17926/) (2023)
- [LAB-Bench: Measuring Capabilities of Language Models for Biology Research](https://mlsanity.com/paper/2407.10362/) (2024)
- [BixBench: a Comprehensive Benchmark for LLM-based Agents in Computational Biology](https://mlsanity.com/paper/2503.00096/) (2025)
- [SpatialBench: Can Agents Analyze Real-World Spatial Biology Data?](https://mlsanity.com/paper/2512.21907/) (2025)

## Built on by (most cited first, 3 of 3)

- [BixBench3: Benchmarking AI agents on research-study-scale computational biology tasks](https://mlsanity.com/paper/2608.25286/) (2026)
- [TxBench-PP: Analyzing AI Agent Performance on Small-Molecule Preclinical Pharmacology](https://mlsanity.com/paper/2606.19245/) (2026)
- [scBench-Long: Verifiable Benchmarking of Long-Horizon Single-Cell Biology](https://mlsanity.com/paper/2606.26563/) (2026)

## Abstract (arXiv)

AI agents are increasingly useful for biological data analysis, but existing benchmarks mostly test broad biological knowledge, executable workflows, or localized analysis steps rather than end-to-end scientific reasoning over spatial measurements. We introduce SpatialBench-Long, a benchmark for long-horizon spatial biology in which agents must recover biological claims from raw or near-raw data and calibrated experimental context without prescribed methods. SpatialBench-Long contains 24 evaluations across primary pancreatic ductal adenocarcinoma (PDAC), engineered glioblastoma organoids and in vivo tumors, Cas9 lineage-traced lung adenocarcinoma, and mouse optic nerve aging/intervention systems, spanning CosMx, Visium, Xenium, multiplexed error-robust fluorescence in situ hybridization (MERFISH), single-cell RNA sequencing (scRNA-seq), Slide-seq, Slide-tags, histology, and lineage-recording data. Candidate claims are hardened through reproduction, independent scientist review, and trajectory inspection. Final answers are graded deterministically over controlled vocabularies and symbols with companion rubrics capturing progress through key analysis chokepoints. Across the SpatialBench-Long benchmark, three model-harness pairs tie at 8/72 runs (11.1%): Gemini 3.5 Flash / Pi terminal coding harness, GPT-5.5 / Pi, and GPT-5.5 / OpenAI Codex. SpatialBench-Long tests whether agents can move beyond executing procedural analysis to deriving accurate scientific conclusions from complex spatial measurements.