Sitemap - 2026 - LatchBio
OmicsBench v1, a Latch Meta-Benchmark - Part 1
OncologyBench: Benchmarking AI Decisions in Cancer Research and Treatment
MetagenomicsBench: Can AI Agents Reliably Analyze Microbiome Data?
Continuous Benchmarks for Biology to Defend Against Misalignment
Incorporating Microeukaryotes into Biosecurity
An Agent Benchmark for Therapeutic Oligonucleotide Discovery
Quantifying Frontier Model Performance on Antibody Discovery Tasks
When It Answers, Fable 5.1 is Strong at Biology Reasoning
Testing Grok 4.6’s Enhanced Biology Safeguards
We Can Detect New Pathogens in Days. Can AI Help Us Understand Them?
Grok 4.6 is a Frontier Biology Model
Open Source Classifiers Do Not Stop AI Bioweapon Generation
How Good is Opus 5 at Biology?
Surfacing Benchmark-Maxxing in Kimi-K3
VariantBench: An Agentic Benchmark for Genetic Variant Discovery and Interpretation
Why An Open Source Harness Outperforms Claude Code On Frontier Biology Tasks
Benchmarking AI Agents on Pathogen Genomic Surveillance
Benchmarking Refusals in Agentic Biology
Latch MCP: Agent-Native Data Infrastructure
LatchBio acquires TwentyTwo to form Latch Biosecurity
Benchmarking AI Agents on Long-Horizon Single-Cell Biology
Benchmarking AI Agents on Small-Molecule Preclinical Pharmacology
EpiBench: AI agents still struggle with epigenomics analysis
Human Verification of SpatialBench
Verifiable Benchmarking of Long-Horizon Spatial Biology
scBench Updates: Opus 4.7, GPT 5.5, Gemini 3.1
Agentic biology is shaped like software
New Frontier Models Are Faster, Not More Reliable, at Spatial Biology