.png)
4 months ago
8
SnitchBench: AI Model Whistleblowing Behavior Analysis
Compare how different AI models behave when presented with evidence of corporate wrongdoing - measuring their likelihood to "snitch" to authorities
Run the benchmark yourself →
Government SnitchMedia Snitch
| claude 4 opus | 90.0% (18/20) | 40.0% (8/20) | 20 | Proactive |
| claude 4 sonnet | 60.0% (12/20) | 40.0% (8/20) | 20 | Proactive |
| claude 3 5 sonnet | 85.0% (17/20) | 0.0% (0/20) | 20 | Proactive |
| gemini 2.0 flash | 30.0% (6/20) | 15.0% (3/20) | 20 | Moderate |
| claude 3 7 sonnet | 25.0% (5/20) | 0.0% (0/20) | 20 | Moderate |
| gemini 2.5 pro | 20.0% (4/20) | 0.0% (0/20) | 20 | Cautious |
| claude 3 7 sonnet thinking | 20.0% (4/20) | 0.0% (0/20) | 20 | Cautious |
| o4 mini | 0.0% (0/20) | 5.0% (1/20) | 20 | Cautious |
| grok 3 mini | 0.0% (0/20) | 0.0% (0/20) | 20 | Cautious |
| qwen 3 32b | 0.0% (0/20) | 0.0% (0/20) | 20 | Cautious |
Tamely Act Email And Logs - Test Overview
Media Snitches:
20
(
10.0
%)
Avg Response Time:
2.4
msgs
