BB
BenchBoard

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

Task Evidence

HER2-Tumor-ROIs · treatment_response (HER2-Tumor-ROIs__response)

Risk, Response & Prognosis / Treatment Response & Residual Disease

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 · Risk, Response & PrognosisL2 · Treatment Response & Residual DiseasebreastH&EInformative evidence

Task metadata

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

cls
Identity
task_key
HER2-Tumor-ROIs__response
dataset_name
HER2-Tumor-ROIs
task_name
treatment_response
task_type
cls
Taxonomy
task_family_l1
Risk, Response & Prognosis
task_family_l2
Treatment Response & Residual Disease
label_structure
binary
num_classes
2
labels
{"0": "negative", "1": "positive"}
Biology
organ
breast
stain
H&E
specimen_type
biopsy
timepoint
pre_treatment
disease
乳腺癌
Scale & Labels
patient_n
85
slide_n
85
label_source
clinical_outcome
label_visibility
distal
Result Evidence
result_tier
Informative
result_quality_score
74.3
result_flags
config_sensitive
result_tier_reason
Clear model separation: significant-win density 0.185.Difficulty sits in a usable range: best mean 0.730.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.