AI Science Research, Security Benchmarks, and Agent Validation Studies Released

연구/벤치마크 | Wed Jun 17 2026 00:00:00 GMT+0000 (Coordinated Universal Time) | 6 sources

OpenAI, Google, and Anthropic released AI agent performance validations and new benchmarks across science, medical, and security domains.

Sources

• [1] A near-autonomous AI chemist improves a challenging reaction in medicinal chemistry - OpenAI Blog
• [2] Introducing LifeSciBench - OpenAI Blog
• [3] New research shows how AMIE, our medical AI, could help manage health conditions. - Google AI Blog
• [4] What we learned mapping a year’s worth of AI-enabled cyber threats - Anthropic News
• [5] Agentic coding and persistent returns to expertise - Anthropic Research
• [6] Paving the way for agents in biology - Anthropic Research