BB
BenchBoard

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

← back to BenchBoard·all tasks

Task Evidence

DLBCL-Morphology · hans_subtype (DLBCL-Morphology__HANS)

Biomarker & Molecular Profiling / Composite Molecular & Immune Phenotypes

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 · Biomarker & Molecular ProfilingL2 · Composite Molecular & Immune PhenotypeslymphomamixedInformative evidence

Task metadata

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

cls
Identity
task_key
DLBCL-Morphology__HANS
dataset_name
DLBCL-Morphology
task_name
hans_subtype
task_type
cls
Taxonomy
task_family_l1
Biomarker & Molecular Profiling
task_family_l2
Composite Molecular & Immune Phenotypes
label_structure
binary
num_classes
2
labels
{"0": "GCB", "1": "non-GCB"}
Biology
organ
lymphoma
stain
mixed
specimen_type
unknown
timepoint
unknown
disease
淋巴瘤
Scale & Labels
patient_n
133
slide_n
184
label_source
ihc_fish
label_visibility
indirect
Result Evidence
result_tier
Informative
result_quality_score
77.1
result_flags
—
result_tier_reason
Clear model separation: significant-win density 0.233.Difficulty sits in a usable range: best mean 0.715.Leader has a visible runner-up gap: 0.089.
loading…

Similar tasks

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