Scientific task · Omics analysis

Omics and cellular analysis

Analyze genome-scale profiles

组学与细胞分析

Omics profileCellTissueOmics analysis

Definition and search aliases

Permanent ID
omics-cellular-analysis
Aliases
omics analysis
Deprecated aliases
None
Hierarchy
Parent task; benchmark coverage below includes its leaf tasks.

Coverage

7 benchmark families cover this task

agentic-evalpartial

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.

Cell-type annotationCell-state clusteringDifferential expression analysisSpatial omics analysis
suitepartial

Single-cell Omics Arena

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

Cell-type annotation
agentic-evalpartial

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.

Omics and cellular analysis
agentic-evalpartial

BixBench

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

Omics and cellular analysis
agentic-evalpartial

CompBioBench

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

Omics and cellular analysis
agentic-evalpartial

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.

Omics and cellular analysis
suitecomplete

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.

Single-cell data integration

Evidence-backed count claims

Each row keeps its original unit and basis. Rows with different units or overlapping mappings are never added.

BenchmarkMapped taskCoverageCountVersionEvidence
SpatialBench
root: spatialbench
Cell-state clustering
official-taxonomy · high
explicitly-in-scope3 problems
official category_results.json n_evals
repo-159-5042c4f
as of 2026-06-10
spatialbench-evidence-current-counts
Single-cell Omics Arena
root: single-cell-omics-arena-soar
Cell-type annotation
official-taxonomy · high
explicitly-in-scope1226 tasks
Benchmark-wide cell-type annotation task total reported by the creator paper.
initial-releasesingle-cell-omics-arena-soar-automated-task-1-evidence
SpatialBench
root: spatialbench
Cell-type annotation
official-taxonomy · high
explicitly-in-scope45 problems
official category_results.json n_evals
repo-159-5042c4f
as of 2026-06-10
spatialbench-evidence-current-counts
SpatialBench
root: spatialbench
Differential expression analysis
official-taxonomy · high
explicitly-in-scope40 problems
official category_results.json n_evals
repo-159-5042c4f
as of 2026-06-10
spatialbench-evidence-current-counts
BioMysteryBench
root: biomysterybench
Omics and cellular analysis
official-taxonomy · high
explicitly-in-scopeNot reported
v11 mystery-bioinformatics problems using omics and cellular data.
v11biomysterybench-evidence-taxonomy
BixBench
root: bixbench
Omics and cellular analysis
official-taxonomy · high
observedNot reported
v1.5 questions carrying official genomics, transcriptomics, epigenomics, single-cell, proteomics, or integrative-omics category labels.
v1.5bixbench-evidence-taxonomy
CompBioBench
root: compbiobench
Omics and cellular analysis
official-taxonomy · high
explicitly-in-scopeNot reported
v1 tasks in official genomics, transcriptomics, epigenetics, single-cell, and spatial domains.
v1compbiobench-evidence-taxonomy
GeneBench-Pro
root: genebench-pro
Omics and cellular analysis
official-taxonomy · high
explicitly-in-scopeNot reported
Problems assigned to transcriptomics, epigenomics, single-cell, spatial, proteomics, microbiome, and related official domains.
paper-v1genebench-pro-paper-evidence
scIB
root: scib
Single-cell data integration
official-taxonomy · high
explicitly-in-scope13 tasks
Atlas-level integration tasks.
paper-2021scib-paper-definition-evidence
SpatialBench
root: spatialbench
Spatial omics analysis
official-taxonomy · high
explicitly-in-scope36 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.

WorkProvider / classRelated runs
Evaluating Claude's bioinformatics research capabilities with BioMysteryBenchAnthropic
benchmark_creator
biomysterybench-official-run
biomysterybench-v8-human-difficult
biomysterybench-v8-human-solvable
BixBench: a Comprehensive Benchmark for LLM-based Agents in Computational BiologyFutureHouse, ScienceMachine
benchmark_creator
bixbench-creator-paper
bixbench-paper-mcq-no-images
bixbench-paper-mcq-no-refusal
bixbench-paper-mcq-refusal
BixBench v1.5 dataset and evaluation releaseFutureHouse, ScienceMachine
benchmark_creator
bixbench-v1-5-agentic-mcq-no-refusal-images
bixbench-v1-5-agentic-mcq-refusal-images
bixbench-v1-5-agentic-mcq-refusal-no-images
bixbench-v1-5-agentic-open-images
bixbench-v1-5-zero-shot-mcq-no-refusal
bixbench-v1-5-zero-shot-mcq-refusal
bixbench-v1-5-zero-shot-open
Agentic systems are adept at solving well-scoped, verifiable problems in computational biologyGenentech, Roche
benchmark_creator
compbiobench-codex-hardest
compbiobench-creator-full
compbiobench-haiku-full
compbiobench-haiku-hardest
compbiobench-nonagentic-baselines
compbiobench-opus-full
compbiobench-opus-hardest
compbiobench-sonnet-full
compbiobench-sonnet-hardest
GeneBench-Pro: Evaluating Multistage Statistical Reasoning in Genomics, Quantitative Biology, and Translational BiomedicineOpenAI
benchmark_creator
genebench-pro-claude-high
genebench-pro-claude-low
genebench-pro-claude-max
genebench-pro-claude-medium
genebench-pro-claude-xhigh
genebench-pro-official
genebench-pro-pro-mode
genebench-pro-reasoning-enabled
genebench-pro-standard-high
genebench-pro-standard-low
genebench-pro-standard-max
genebench-pro-standard-medium
genebench-pro-standard-none
Benchmarking atlas-level data integration in single-cell genomicsHelmholtz Zentrum München, Technical University of Munich
benchmark_creator
scib-creator-full
Single-cell Omics Arena repository result snapshotUniversity of California, Irvine
benchmark_creator
soar-e5d2b3e-rna-zero-shot
soar-e5d2b3e-rna-zero-shot-cot
SpatialBench: Can Agents Analyze Real-World Spatial Biology Data?LatchBio
benchmark_creator
spatialbench-paper-v2-base
spatialbench-paper-v2-claude-code
spatialbench-paper-v2-latch
SpatialBench 159-evaluation repository snapshotLatchBio
benchmark_creator
spatialbench-repo-159-claude-code
spatialbench-repo-159-mini-swe-agent
spatialbench-repo-159-openai-codex
spatialbench-repo-159-pi