CompBioBench
A 100-task agent benchmark of objectively gradable computational-biology problems requiring multi-step reasoning, bespoke code, tools, and real-world external resources.
Scientific domain
Spatial omics
Spatially resolved molecular measurements and analyses.
空间组学
4 registered benchmarks and tracks
GeneBench-Pro
A research-level agent benchmark of 129 synthetic, multistage computational-biology analyses that require iterative QC, statistical modeling, diagnostics, and decision-relevant judgment.
LifeSciBench
Expert-authored, artifact-rich free-response tasks that evaluate realistic research judgment across applied life-science workflows.
SpatialBench
A benchmark of deterministic, verifiable agentic problems derived from real spatial-transcriptomics workflows, testing whether agents can manipulate data and recover key biological results.
Capability coverage
Registry records tagged Spatial omics, counted by capability.
Accessible data table
| Capability | Records |
|---|---|
| Evidence synthesis | 1 |
| Retrieval | 2 |
| Design | 1 |
| Generation | 1 |
| Optimization | 1 |
| Data analysis | 4 |
| Coding | 3 |
| Tool use | 3 |
| Experiment planning | 1 |
| Troubleshooting | 1 |
| Scientific reasoning | 4 |
| Scientific communication | 1 |
Scientific Tasks in this domain
Task mappings are evidence-backed and may be partial for mixed suites.
Coverage-gap reading: zero counts indicate a gap in this registry, not proof that no benchmark exists. Propose a primary source through the contribution form.