Article

Benchmarking large language models for ACMG/AMP variant interpretation and variant calling

2026-07-05

Abstract excerpt

Agentic large language models are increasingly used across the genomic workflow, from variant calling to clinical interpretation, yet they are evaluated by accuracy alone, a single figure that cannot say whether a system is safe or where in the workflow a failure originates. We present ClawBench, a framework that attributes each outcome to the architectural layer that produced it across both halves of the canonica...

Topics

Open a Topic to create a Post that cites this publication.

Identifiers and source

Literature Corpus work: 27006277-8463-5c5b-9f7b-3b71b4d42169
DOI: 10.64898/2026.06.30.735646

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

Benchmarking large language models for ACMG/AMP variant interpretation and variant callingDOI 10.64898/2026.06.30.735646Read

Evaluating open LLMs for agentic analysis orchestration in a typical biomedical labSemantic proximity Read

Trustworthy agentic genomics through versioned skill librariesSemantic proximity Read

Client-server interfaces enable efficient agent-driven variant callingSemantic proximity Read

AIVA: An Agentic Platform for Phenotype-Aware Variant Analysis, Interpretation and Clinical Decision Support in Rare DiseaseSemantic proximity Read

Grounding Health AI: Architecture and Evaluation of a Domain-Expert Metabolic Health AgentSemantic proximity Read

BiomniBench: Process-level Evaluation of LLM Agents for Real-world Biomedical ResearchSemantic proximity Read

ChromSkills enables interpretable and reproducible agentic chromatin data analysisSemantic proximity Read

A Biosecurity Agent for Lifecycle LLM Biosecurity AlignmentSemantic proximity Read

Beyond Benchmarks: Dynamic, Automatic And Systematic Red-Teaming Agents For Trustworthy Medical Language ModelsSemantic proximity Read

FHIR-AgentEval: A Modular Sandbox for Benchmarking Clinical LLM Agents with an Evaluation of Memory-Augmented ConfigurationsSemantic proximity Read

MARRVEL-MCP: An agentic interface for Mendelian disease discovery via tool-augmented context engineering.Semantic proximity Read

Agentomics: An Agentic System that Autonomously Develops Novel State-of-the-art Solutions for Biomedical Machine Learning TasksSemantic proximity Read