When Better Means Less: Quantifying What Benchmarks Miss Between Model Generations. 2,310 controlled comparisons show GPT-5 series lost 6.7x creativity and gained 4.4x false refusals vs chatgpt-4o-latest — invisible to standard benchmarks.

An exploration or the contradictions of Google Family of LLMs

Base Qwen/qwen:2.5-coder:1.5b model, fine-tuned for MAX performance on Agentic Tasks and Ecosystems. Surpassed Base Model on Python/Typescript Coding Workfoads.

From TextBlob to LLM Agents — sentiment model selection for B2B technical support with CSAT ground truth (ACL 2026 Industry Track). Paper, figures, aggregate results, poster & slides.