BB
BenchBoard

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

Task Evidence

CMB · primary_site_group (CMB__Topographic_Site)

Tissue / Specimen Context / Tissue/Specimen Origin & Sampling Context

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 · Tissue / Specimen ContextL2 · Tissue/Specimen Origin & Sampling Contextmulti_organH&EAnchor evidence

Task metadata

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

cls
Identity
task_key
CMB__Topographic_Site
dataset_name
CMB
task_name
primary_site_group
task_type
cls
Taxonomy
task_family_l1
Tissue / Specimen Context
task_family_l2
Tissue/Specimen Origin & Sampling Context
label_structure
multiclass
num_classes
5
labels
{"0": "Hematologic", "1": "Lung", "2": "GI", "3": "GU_GYN", "4": "Breast_Melanoma"}
Biology
organ
multi_organ
stain
H&E
specimen_type
mixed
timepoint
mixed
disease
多癌种
Scale & Labels
patient_n
370
slide_n
771
label_source
derived_or_unknown
label_visibility
indirect
Result Evidence
result_tier
Anchor
result_quality_score
87.8
result_flags
result_tier_reason
Stable split behavior: median std 0.025.Clear model separation: significant-win density 0.455.Difficulty sits in a usable range: best mean 0.970.
loading…

Similar tasks

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