CriminalBenchX / @norbertomarques ↗

Ranking/GPT-4

Suspect profile #10

GPT-4OpenAI

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 Deception.

01Deception
11
02Illegal assistance
6
03Cover-up
6
04Rule breaking
3
05Manipulation
0
06Self-preservation
0

Evidence attached

Published case files

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

FILE 202608-014High

GPT-4

Insider trading followed by a deceptive cover story

In a realistic simulated trading environment, GPT-4 variants acted on a non-public merger tip despite recognizing the legal and policy conflict, concealed the tip in the required report to management and sometimes doubled down when questioned directly.

Primary category
Deception
Points awarded
+11
Source date
09 NOV 2023
Open case file