🧠 Evaluating Reasoning in LLMs: Benchmark & Chain-of-Thought Verification Lab

Watch an LLM benchmark grid get scored live: tune task difficulty, chain-of-thought length, tool-assisted verification and self-consistency sampling, and see accuracy, compute cost and seed variance respond in real time.

3D · Three.js / WebGL renderer · 60 FPS target · runs fully client-side, no install