AGIdex
agidex/Capabilities/Learning/Few-shot Learning
SUB-CAPABILITY · LEARNING

Few-shot Learning

76%
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

Learn a new task from a handful of demonstrations a teacher would give a student.

Human frontier

Match expert performance from 1–3 examples on genuinely novel domain tasks.

Current state

What works

In-context learning of NLP tasks; tool use from a single demonstration.

Key gaps

Tasks requiring procedural fluency rather than pattern recognition from examples.

Evidence

0 sources
TechnologyQualitySourceScore vs. baselineScore
No evidence records yet.