BB
BenchBoard

Decision cockpit for pathology foundation-model benchmarking, built to move from broad coverage scans to task-level evidence.

Task Evidence

IMP-Cervical · cervical_dysplasia_grade (IMP-Cervical__subtype)

Diagnostic Pathology / Histologic Grading & Dysplasia Severity

Inspect benchmark evidence for one task at a time: who leads, how stable the split-level results are, and which neighbouring tasks are likely to transfer intuition.

clsL1 · Diagnostic PathologyL2 · Histologic Grading & Dysplasia SeveritycervicalH&EAnchor evidence

Task metadata

Fields sourced from benchmark_main. Missing values are shown as —.

cls
Identity
task_key
IMP-Cervical__subtype
dataset_name
IMP-Cervical
task_name
cervical_dysplasia_grade
task_type
cls
Taxonomy
task_family_l1
Diagnostic Pathology
task_family_l2
Histologic Grading & Dysplasia Severity
label_structure
multiclass
num_classes
4
labels
{"0": "Non-neoplastic (NNeo)", "1": "Low-grade squamous intraepithelial lesion (LSIL)", "2": "High-grade squamous intraepithelial lesion (HSIL)", "3": "Non-representative (other)"}
Biology
organ
cervical
stain
H&E
specimen_type
resection
timepoint
diagnosis
disease
宫颈癌
Scale & Labels
patient_n
599
slide_n
599
label_source
pathology
label_visibility
direct
Result Evidence
result_tier
Anchor
result_quality_score
87.9
result_flags
result_tier_reason
Stable split behavior: median std 0.023.Clear model separation: significant-win density 0.424.Difficulty sits in a usable range: best mean 0.932.
loading…

Similar tasks

Ranked by shared L2 subtype first, then L1 family, organ, type and label structure.