The latest nullbench run used the revised judge panel with glm-4-9b as the mid judge. The swap cut family correlation and exposed variance that earlier Qwen-anchored panels smoothed over. The aggregate scores confirm the …
Building on the previous nullbench1 methodology and early refinements2, we expanded the pool, kept decoding and scoring fixed, and asked if these additions change routing. The primary harness still scores answers only …
RAG pipelines retrieve a narrow slice of documents that look closest in vector space to a query, but treating that narrowing as discovery ignores the fact that anything framed outside familiar patterns is never even …
The way people reach information is undergoing a structural break. For two decades, the web grew on the back of search engines sending users outward: a query produced links, traffic flowed to publishers, and the …
NVIDIA’s June 2025 paper Small Language Models Are the Future of Agentic AI argues that agent systems run better when built around small language models (SLMs) rather than leaning exclusively on large ones1. A …
We revised nullbench with a stability metric that avoids collapse on single spikes and a category set split into more granular writing style and language comprehension tracks. The overall portfolio remains the same1, but …
Large language models capable of acting as agents introduces a new layer of risk. These systems are more than passive text generators but are often equipped with tools and can increasingly get wired into developer …
Control of execution defines ownership. When a large language model file sits on your machine, it runs the same way until you decide to replace it. No silent updates, no routed experiments, no persona patches. When …
Evaluation of large language models (LLMs) is often presented as a leaderboard problem, ranking systems by performance on tasks with clear, objective answers. Prior work showed that such leaderboards hide collapse …
Nullbench is a controlled, reproducible benchmarking framework for large language models (LLMs) designed to isolate inherent response tendencies by evaluating models in a zero-context environment. Unlike ubiquitous …