AGIdex
agidex/Capabilities/Learning/Transfer Learning
SUB-CAPABILITY · LEARNING

Transfer Learning

68%
vs. HUMAN BASELINE = 100
PartialConf · Medium

Scoring rubric

0–20
Early research
20–40
Narrow benchmark competence
40–60
Strong benchmark · reliability gaps
60–80
Human-competitive in common scenarios
80–100
Comparable to typical skilled adult
100+
Reliably exceeds typical human baseline

Score vs. baseline

Trend · Last 12 months
12mo ago   %
6mo ago   %
Today   %
Δ 12mo   +0

What this measures

Human baseline

Apply a skill from one task to a closely related task without full retraining.

Human frontier

Transfer across modalities and structurally different task domains reliably.

Current state

What works

Within-modality transfer is robust; fine-tuning on small datasets generalizes well.

Key gaps

Cross-modal transfer to embodied tasks; transfer to domains with different reasoning structure.

Evidence

0 sources
TechnologyQualitySourceScore vs. baselineScore
No evidence records yet.