BixBench3: Benchmarking AI agents on research-study-scale computational biology tasks

arXiv:2608.25286 · cs.AI, q-bio.QM · Submitted 2026-08-26 · Read on arXiv

cs.AI, q-bio.QM

Submitted: 2026-08-26

Updated: 2026-09-22

Code: https://github.com/UKGovernmentBEIS/inspect_ai

Terminology

• Benchmark — 26× in this paper · explained in 2 episodes
• Abundance — 22× in this paper · explained in 1 episode
• AI Agents — 11× in this paper · explained in 2 episodes
• Benchmarking — 8× in this paper · explained in 3 episodes
• Computational Biology — 6× in this paper · explained in 2 episodes
• Failure Modes — 5× in this paper · explained in 3 episodes
• Agent Harness — 2× in this paper · explained in 2 episodes
• Core — 2× in this paper · explained in 2 episodes
• LLM judge — 2× in this paper · explained in 2 episodes
• Accuracy — 1× in this paper · explained in 1 episode
• Agent Architectures — 1× in this paper · explained in 1 episode
• Agentic AI — 1× in this paper · explained in 1 episode
• Agentic System — 1× in this paper · explained in 2 episodes
• Artificial Intelligence (AI) — 1× in this paper · explained in 2 episodes
• Commentary — 1× in this paper · explained in 2 episodes
• F1 Score — 1× in this paper · explained in 3 episodes
• Foundation Model — 1× in this paper · explained in 3 episodes
• Foundation Models — 1× in this paper · explained in 7 episodes
• Large Language Models (LLMs) — 1× in this paper · explained in 6 episodes
• Multi-Agent System — 1× in this paper · explained in 6 episodes
• Trace — 1× in this paper · explained in 2 episodes
• World Model — 1× in this paper · explained in 7 episodes

Sources

• SWE-Marathon: Can Agents Autonomously Complete Ultra-Long-Horizon Software Work?
• Verifiable Benchmarking of Long-Horizon Spatial Biology
• scBench-Long: Verifiable Benchmarking of Long-Horizon Single-Cell Biology
• LAB-Bench: Measuring Capabilities of Language Models for Biology Research
• LABBench2: An Improved Benchmark for AI Systems Performing Biology Research
• GenoTEX: An LLM Agent Benchmark for Automated Gene Expression Data Analysis
• BioProBench: A Corpus and Benchmark for Biological Protocol Reasoning in Autonomous Science
• Benchmarking AI scientists for omics data driven biological discovery
• Agentomics-ML: Autonomous Machine Learning Experimentation Agent for Genomic and Transcriptomic Data
• Terminal-Bench: Benchmarking Agents on Hard, Realistic Tasks in Command Line Interfaces
• BixBench: a Comprehensive Benchmark for LLM-based Agents in Computational Biology
• Kosmos: An AI Scientist for Autonomous Discovery
• HCAST: Human-Calibrated Autonomy Software Tasks
• BioDSA-1K: Benchmarking Data Science Agents for Biomedical Research

Related papers

• MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
• Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
• The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
• MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
• Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems
• VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection