LAB-Bench
A practical biology-research suite of 2,457 multiple-choice questions across eight broad categories and 31 versioned task files, with public and private contamination-monitoring splits.
Scientific task · Scientific workflow
Experiment and protocol planning
Design an experiment
实验与方案规划
Definition and search aliases
- Permanent ID
experiment-protocol-planning- Aliases
- experimental design, protocol design
- Deprecated aliases
- None
- Hierarchy
- Leaf task under Scientific workflow and systems analysis
Coverage
1 benchmark families cover this task
LAB-Bench CloningScenarios
Human-hard, multi-step multiple-choice scenarios involving plasmids, DNA fragments, enzymes, and molecular-cloning workflows.
LAB-Bench ProtocolQA
Troubleshoots intentionally modified published biological protocols by selecting steps that would repair the stated outcome.
Evidence-backed count claims
Each row keeps its original unit and basis. Rows with different units or overlapping mappings are never added.
| Benchmark | Mapped task | Coverage | Count | Version | Evidence |
|---|---|---|---|---|---|
| LAB-Bench root: lab-bench | Experiment and protocol planning official-track · high | explicitly-in-scope | 135 questions ProtocolQA questions across public and private splits. | repository-998a8e0 | lab-bench-evidence-paper |
| LAB-Bench CloningScenarios root: lab-bench | Experiment and protocol planning official-track · high | explicitly-in-scope | 41 questions questions across public and private splits | repository-998a8e0 | lab-bench-cloning-scenarios-evidence-paper |
| LAB-Bench ProtocolQA root: lab-bench | Experiment and protocol planning official-track · high | explicitly-in-scope | 135 questions questions across public and private splits | repository-998a8e0 | lab-bench-protocolqa-evidence-paper |
Official evaluations connected to these benchmarks
Runs are included only for benchmark records mapped here (and formal child tracks when a mapped suite is the root). A task mapping does not imply that every run isolates this task.