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.
Scientific task · Cellular and spatial analysis
Spatial omics analysis
Analyze spatially resolved molecular profiles
空间组学分析
Definition and search aliases
- Permanent ID
spatial-omics-analysis- Aliases
- spatial domain analysis, spatial transcriptomics
- Deprecated aliases
- None
- Hierarchy
- Leaf task under Omics and cellular analysis
Coverage
1 benchmark families cover this task
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 |
|---|---|---|---|---|---|
| SpatialBench root: spatialbench | Spatial omics analysis official-taxonomy · high | explicitly-in-scope | 36 problems official category_results.json n_evals | repo-159-5042c4f as of 2026-06-10 | spatialbench-evidence-current-counts |
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.
| Work | Provider / class | Related runs |
|---|---|---|
| SpatialBench: Can Agents Analyze Real-World Spatial Biology Data? | LatchBio benchmark_creator | spatialbench-paper-v2-basespatialbench-paper-v2-claude-codespatialbench-paper-v2-latch |
| SpatialBench 159-evaluation repository snapshot | LatchBio benchmark_creator | spatialbench-repo-159-claude-codespatialbench-repo-159-mini-swe-agentspatialbench-repo-159-openai-codexspatialbench-repo-159-pi |