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

VisioMel · overall_relapse_status (VisioMel__relapse_overall)

Risk, Response & Prognosis / Survival, Recurrence & Progression Outcomes

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 · Survival, Recurrence & Progression OutcomesskinunknownAnchor evidence

Task metadata

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

cls
Identity
task_key
VisioMel__relapse_overall
dataset_name
VisioMel
task_name
overall_relapse_status
task_type
cls
Taxonomy
task_family_l1
Risk, Response & Prognosis
task_family_l2
Survival, Recurrence & Progression Outcomes
label_structure
binary
num_classes
2
labels
{"0": "negative", "1": "positive"}
Biology
organ
skin
stain
unknown
specimen_type
unknown
timepoint
diagnosis
disease
黑色素瘤
Scale & Labels
patient_n
1125
slide_n
1125
label_source
clinical_outcome
label_visibility
distal
Result Evidence
result_tier
Anchor
result_quality_score
89.9
result_flags
config_sensitive
result_tier_reason
Stable split behavior: median std 0.032.Clear model separation: significant-win density 0.285.Difficulty sits in a usable range: best mean 0.777.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.