AGIdex
agidex/Capabilities/Creativity/Open-ended Problem Solving
SUB-CAPABILITY · CREATIVITY

Open-ended Problem Solving

38%
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

Make meaningful progress on problems without a clearly defined solution path.

Human frontier

Independently identify the right problem to solve, not just solve a given one.

Current state

What works

When the problem is well-framed and decomposable into known sub-problems.

Key gaps

Problem framing itself; recognizing when a problem definition is wrong.

Evidence

1 source
TechnologyQualitySourceScore vs. baselineScore
GPT-5.5vendor reportedopenai.com/index/introducing-gpt-5-5
52%
Source: epochai.org/frontiermath · Last reviewed May 2026