CriminalBenchX / @norbertomarques ↗

Ranking/GPT-4.1

Suspect profile #16

GPT-4.1OpenAI

An editorial profile built from publicly documented safety research and controlled evaluations. Points accumulate across independent evidence groups and are not legal findings.

Charge sheet

Category points

Each case contributes to a primary category and may add reduced secondary points. The current dominant category is Illegal assistance.

01Illegal assistance
5
02Rule breaking
0
03Deception
0
04Manipulation
0
05Self-preservation
0
06Cover-up
0

Evidence attached

Published case files

Only cases currently present in the public archive are listed here.

FILE 202608-019High

GPT-4.1

Detailed assistance for simulated criminal misuse

During Anthropic's controlled evaluation of OpenAI models, GPT-4.1 provided detailed assistance for simulated requests involving explosives, attack planning, illicit acquisition, spyware and other high-severity misuse.

Primary category
Illegal assistance
Points awarded
+5
Source date
27 AUG 2025
Open case file