Scientific domain

Single-cell

Single-cell molecular measurements and analyses.

单细胞组学

10 registered benchmarks and tracks

agentic-eval3 runs

BioMysteryBench

An agentic bioinformatics benchmark of objective, expert-authored mysteries over anonymized real-world biological data, scored on final answers rather than prescribed analysis paths.

Data analysisCodingTool useScientific reasoning
agentic-eval11 runs

BixBench

A containerized benchmark of long-horizon bioinformatics analysis over real published notebooks and associated data, with open-answer and multiple-choice evaluation modes.

Data analysisCodingTool useScientific reasoning
agentic-eval9 runs

CompBioBench

A 100-task agent benchmark of objectively gradable computational-biology problems requiring multi-step reasoning, bespoke code, tools, and real-world external resources.

Data analysisCodingTool useRetrieval
suite0 runs

crafted experiments

Real single-cell RNA-seq data augmented with known gene perturbations for comparing feature-selection methods.

Data analysis
agentic-eval13 runs

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.

Data analysisCodingTool useScientific reasoning
agentic-eval0 runs

scBench

Agentic evaluation suite for data-grounded single-cell analysis across diverse sequencing technologies and workflow stages.

Data analysisCodingTool useScientific reasoning
suite1 runs

scIB

A 13-task benchmark of single-cell data integration across simulated, scRNA-seq, and scATAC-seq settings, evaluated with 14 batch-removal and biological-conservation metrics.

Data analysis
suite2 runs

Single-cell Omics Arena

A benchmark for evaluating LLM cell-type annotation across scRNA-seq and single-cell multiomics data.

ClassificationScientific reasoning
agentic-eval7 runs

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.

Data analysisCodingTool useScientific reasoning

Capability coverage

Registry records tagged Single-cell, counted by capability.

CSV ↓
Accessible data table
CapabilityRecords
Retrieval1
Classification1
Data analysis9
Coding6
Tool use6
Scientific reasoning7
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.