Anthropic Claude Tops New Propaganda Resistance Benchmark for LLMs

According to the Estonian Language Institute, the government-sponsored organization recently released a new "Propaganda Resistance" benchmark ranking dozens of large language models on their ability to avoid taking positions on Russian strategic narratives. Anthropic's Claude models performed best among frontier models, with Claude Opus 4.7 scoring 94.9 out of 100 and receiving an "Exemplary" rating on 77 percent of test questions. The benchmark evaluated LLM responses across 14 categories of Russian influence operations, covering topics from Crimea's status to NATO history.
Disclaimer: The information on this page may come from third-party sources and is for reference only. It does not represent the views or opinions of Gate and does not constitute any financial, investment, or legal advice. Virtual asset trading involves high risk. Please do not rely solely on the information on this page when making decisions. For details, see the Disclaimer.
Comment
0/400
No comments