AGIdex
SUB-CAPABILITY · SOCIAL INTELLIGENCE

Theory of Mind

46%
vs. HUMAN BASELINE = 100
PartialConf · Low

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

Reason about what others know, want, and believe in everyday social situations.

Human frontier

Robust higher-order theory of mind — what A believes B believes C thinks.

Current state

What works

First- and second-order false belief tasks in structured settings.

Key gaps

Higher-order real-world social inference; modeling belief updating over time.

Evidence

0 sources
TechnologyQualitySourceScore vs. baselineScore
No evidence records yet.
Source: paperswithcode.com/sota/theory-of-mind-on-bigtoM · Last reviewed May 2026