BB
BenchBoard

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

Task Evidence

EBRAINS · diagnosis (EBRAINS__diagnosis)

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 DiagnosisbrainH&EAnchor evidence

Task metadata

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

cls
Identity
task_key
EBRAINS__diagnosis
dataset_name
EBRAINS
task_name
diagnosis
task_type
cls
Taxonomy
task_family_l1
Diagnostic Pathology
task_family_l2
Disease Entity & Histologic Diagnosis
label_structure
multiclass
num_classes
30
labels
{"0": "Glioblastoma, IDH-wildtype", "1": "Gliosarcoma", "2": "Transitional meningioma", "3": "Anaplastic meningioma", "4": "Pituitary adenoma", "5": "Oligodendroglioma, IDH-mutant and 1p/19q codeleted", "6": "Haemangioma", "7": "Ganglioglioma", "8": "Pilocytic astrocytoma", "9": "Schwannoma", "10": "Anaplastic oligodendroglioma, IDH-mutant and 1p/19q codeleted", "11": "Fibrous meningioma", "12": "Anaplastic astrocytoma, IDH-wildtype", "13": "Angiomatous meningioma", "14": "Haemangioblastoma", "15": "Adamantinomatous craniopharyngioma", "16": "Anaplastic astrocytoma, IDH-mutant", "17": "Glioblastoma, IDH-mutant", "18": "Diffuse astrocytoma, IDH-mutant", "19": "Ependymoma", "20": "Anaplastic ependymoma", "21": "Atypical meningioma", "22": "Metastatic tumours", "23": "Meningothelial meningioma", "24": "Langerhans cell histiocytosis", "25": "Diffuse large B-cell lymphoma of the CNS", "26": "Secretory meningioma", "27": "Haemangiopericytoma", "28": "Lipoma", "29": "Medulloblastoma, non-WNT/non-SHH"}
Biology
organ
brain
stain
H&E
specimen_type
resection
timepoint
mixed
disease
脑肿瘤
Scale & Labels
patient_n
2142
slide_n
2312
label_source
pathology
label_visibility
indirect
Result Evidence
result_tier
Anchor
result_quality_score
85.8
result_flags
crowded_head
result_tier_reason
Stable split behavior: median std 0.004.Clear model separation: significant-win density 0.463.Difficulty sits in a usable range: best mean 0.984.Many contenders sit near the best score: 37.2% within 0.01.
loading…

Similar tasks

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