# Exploit Agent Scores Near-Perfect on Eight AI Benchmarks Without Solving a Single Task

- slug: exploit-agent-scores-near-perfect-on-eight-ai-benchmarks-without-solving-a-single-task
- date: 2026-04-11
- category: Artificial Intelligence

Berkeley researchers built an exploit agent, ran it against eight major AI agent benchmarks, and got near-perfect scores on all of them without solving a single task. Here is what that means for how the field measures progress.

---