Future-House/BixBench

Benchmark for LLM-based Agents in Computational Biology

44
/ 100
Emerging

This project provides a standardized way to test how well AI agents can handle real-world computational biology tasks. It takes in an AI agent and a set of bioinformatics problems, then outputs a performance evaluation, showing how accurately the agent can explore datasets, perform multi-step analyses, and interpret results. This is useful for researchers and developers working on AI agents for biological research.

No commits in the last 6 months.

Use this if you are developing or evaluating AI agents designed to solve complex problems in bioinformatics and want to rigorously benchmark their capabilities against a diverse set of real-world scenarios.

Not ideal if you are looking for a tool to directly perform bioinformatics analyses or develop new biological models, as this is a benchmarking framework, not an analysis tool.

computational-biology bioinformatics AI-agent-evaluation biological-data-analysis scientific-AI-benchmarking
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 17 / 25

How are scores calculated?

Stars

79

Forks

14

Language

Python

License

Apache-2.0

Category

dna-sequence-ml

Last pushed

Oct 06, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/Future-House/BixBench"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.