New benchmark tests LLMs on animal welfare during adversarial conversations

Researchers have developed MANTA, a new benchmark designed to evaluate how well large language models maintain their ethical stances on animal welfare during multi-turn adversarial conversations. The benchmark consists of 1,088 five-turn dialogues that test both value stability and moral sensitivity. When tested on seven frontier models, including Claude Opus 4.7 and GPT-5.5, MANTA revealed that some models' performance rankings shifted significantly under sustained pressure, indicating a potential degradation of their alignment. AI

IMPACT This benchmark could reveal vulnerabilities in LLM alignment, prompting developers to improve robustness against adversarial pressure in sensitive ethical domains.

RANK_REASON The cluster contains an academic paper introducing a new benchmark for evaluating LLM behavior. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.AI →

• Claude Opus 4.7
• DeepSeek V4
• Gemini 3.1 Flash Lite
• GPT-5.5
• Grok 4.3
• Llama 3.3 70B
• MANTA
• Mistral Small

• paper
• safety

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →