BB
BenchBoard

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

Task Evidence

CMB · hematologic_subtype (CMB__heme_subtype)

Diagnostic Pathology / Disease Entity & Histologic Diagnosis

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 · Disease Entity & Histologic Diagnosismulti_organH&EInformative evidence

Task metadata

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

cls
Identity
task_key
CMB__heme_subtype
dataset_name
CMB
task_name
hematologic_subtype
task_type
cls
Taxonomy
task_family_l1
Diagnostic Pathology
task_family_l2
Disease Entity & Histologic Diagnosis
label_structure
binary
num_classes
2
labels
{"0": "Myeloma", "1": "AML"}
Biology
organ
multi_organ
stain
H&E
specimen_type
hematologic
timepoint
mixed
disease
多癌种
Scale & Labels
patient_n
98
slide_n
290
label_source
derived_or_unknown
label_visibility
direct
Result Evidence
result_tier
Informative
result_quality_score
77.5
result_flags
config_sensitive
result_tier_reason
Clear model separation: significant-win density 0.257.Difficulty sits in a usable range: best mean 0.908.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.