BixBench: a Comprehensive Benchmark for LLM-based Agents in Computational Biology
This addresses the problem of measuring progress in AI-driven scientific discovery for researchers in bioinformatics, though it is incremental as it builds on existing benchmarking trends.
The authors tackled the lack of benchmarks for LLM-based agents in computational biology by introducing BixBench, a dataset with over 50 real-world scenarios and nearly 300 open-answer questions, and found that frontier models like GPT-4o and Claude 3.5 Sonnet achieved only 17% accuracy in open-answer tasks.
Large Language Models (LLMs) and LLM-based agents show great promise in accelerating scientific research. Existing benchmarks for measuring this potential and guiding future development continue to evolve from pure recall and rote knowledge tasks, towards more practical work such as literature review and experimental planning. Bioinformatics is a domain where fully autonomous AI-driven discovery may be near, but no extensive benchmarks for measuring progress have been introduced to date. We therefore present the Bioinformatics Benchmark (BixBench), a dataset comprising over 50 real-world scenarios of practical biological data analysis with nearly 300 associated open-answer questions designed to measure the ability of LLM-based agents to explore biological datasets, perform long, multi-step analytical trajectories, and interpret the nuanced results of those analyses. We evaluate the performance of two frontier LLMs (GPT-4o and Claude 3.5 Sonnet) using a custom agent framework we open source. We find that even the latest frontier models only achieve 17% accuracy in the open-answer regime, and no better than random in a multiple-choice setting. By exposing the current limitations of frontier models, we hope BixBench can spur the development of agents capable of conducting rigorous bioinformatic analysis and accelerate scientific discovery.