# EpiBench: Verifiable Evaluation of AI Agents on Epigenomics Analysis

arXiv: https://arxiv.org/abs/2606.13602 · HTML: https://mlsanity.com/paper/2606.13602/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Medical and scientific domain agents, one of 16 directions in LLM agents and tool use.
- Builds on 3 of its 17 references that are in the map.
- First posted on arXiv 11 Jun 2026.

## Placed in

- LLM agents and tool use / [Medical and scientific domain agents](https://mlsanity.com/agents/medical-and-scientific-domain-agents/)

## Builds on (most cited first, 3 of 3)

- [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, 1 of 1)

- [BioSecBench-Surveillance: A Verifiable Benchmark for AI Agents in Pathogen Genomic Surveillance](https://mlsanity.com/paper/2607.19262/) (2026)

## Abstract (arXiv)

We introduce EpiBench, a verifiable benchmark for short-horizon epigenomics analysis. EpiBench evaluates whether agents can make well-defined analysis decisions from realistic workflow states and return deterministically gradable answers. The benchmark includes 106 evaluations across CUT&Tag/CUT&RUN, ATAC-seq, ChIP-seq, and DNA methylation workflows. Across 5,088 valid trajectories from 16 model-harness pairs, no system passed a majority of attempts: GPT-5.5 / Pi led at 45.0% (143/318 attempts; 95% confidence interval (CI), 36.3--53.7), followed by GPT-5.5 / OpenAI Codex at 39.9% (127/318 attempts; 95% CI, 31.6--48.3). Claude Opus 4.8 Max / Pi and GPT-5.4 / Pi each passed 39.0% (124/318 attempts; 95% CI, 30.2--47.8 and 31.0--47.0, respectively). Performance varies across assay types, and many failed runs still contain parts of the correct answer. Agents often found the right files and computed useful intermediate results, but failed when the task required deeper, assay-specific scientific judgment.