↓ Skip to main content

Benchmarks

ZelusBench: Measuring LLM Attention with Geometry

ZelusBench: Measuring LLM Attention with Geometry

·685 words·4 mins
LLM Evaluation Benchmarks Attention
For the Google DeepMind AGI hackathon I took on the attention pathway—a genuinely hard thing to measure. My answer was to make relevance a mathematical fact instead of a judgement call: ZelusBench grounds attention tasks in 3D geometry, and the results reveal distinct cognitive profiles across frontier models.