LatchBio

LatchBio

Home
Archive
About
Incorporating Microeukaryotes into Biosecurity
Toward More Comprehensive AI Safeguards
 • Vanessa Smilansky
An Agent Benchmark for Therapeutic Oligonucleotide Discovery
Benchmarking AI agents on experimentally grounded decisions in ASO/siRNA discovery
 • Martin Jacko, Dillon Flood, Alex Urrutia, Jackson Brougher, and Kenny Workman
Quantifying Frontier Model Performance on Antibody Discovery Tasks
Benchmarking frontier AI agents on the scientific decisions that drive therapeutic antibody discovery
 • Ramesh Ramasamy, Alex Urrutia, and Sean Poust
When It Answers, Fable 5.1 is Strong at Biology Reasoning
An analysis of performance across our benchmark suite
 • Arjun Banerjee
Testing Grok 4.6’s Enhanced Biology Safeguards
Analyzing performance of the new safeguards across our benchmark suite
 • Arjun Banerjee

August 2026

July 2026

How Good is Opus 5 at Biology?
An in depth analysis across our benchmark suite
 • Arjun Banerjee
Surfacing Benchmark-Maxxing in Kimi-K3
Today we released results for Kimi-K3, an open-source LLM boasting GPT-5.6/Mythos-level coding-benchmark scores, across our short-horizon therapeutics…
 • Arjun Banerjee
VariantBench: An Agentic Benchmark for Genetic Variant Discovery and Interpretation
A verifiable benchmark for variant discovery, statistical genetics, and personal genomics
 • Kenny Workman and Christopher Zou
Why An Open Source Harness Outperforms Claude Code On Frontier Biology Tasks
In current generation models, behavioral priors introduce by harnesses such as Claude Code, and Codex cause substantial performance swings on our…
 • Joel Simonoff
© 2026 LatchBio · Privacy ∙ Terms ∙ Collection notice
Start your SubstackGet the app
Substack is the home for great culture