BB
BenchBoard

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

Task Evidence

HANCOCK · sample_origin_type (Hancock__primarily_metastasis)

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 Contexthead/neckH&EInformative evidence

Task metadata

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

cls
Identity
task_key
Hancock__primarily_metastasis
dataset_name
HANCOCK
task_name
sample_origin_type
task_type
cls
Taxonomy
task_family_l1
Tissue / Specimen Context
task_family_l2
Tissue/Specimen Origin & Sampling Context
label_structure
binary
num_classes
2
labels
{"0": "Primary", "1": "Metastasis"}
Biology
organ
head/neck
stain
H&E
specimen_type
resection
timepoint
diagnosis
disease
头颈部癌
Scale & Labels
patient_n
673
slide_n
681
label_source
clinical_baseline
label_visibility
unknown
Result Evidence
result_tier
Informative
result_quality_score
76.4
result_flags
config_sensitive
result_tier_reason
Clear model separation: significant-win density 0.176.Difficulty sits in a usable range: best mean 0.700.Leader changes across checkpoint strategies: 3 distinct leaders.
loading…

Similar tasks

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