AI RESEARCH
OckBench: Measuring the Efficiency of LLM Reasoning
arXiv CS.AI
•
ArXi:2511.05722v3 Announce Type: replace-cross Large language models (LLMs) such as GPT-5 and Gemini 3 have pushed the frontier of automated reasoning and code generation. Yet current benchmarks emphasize accuracy and output quality, neglecting a critical dimension: efficiency of token usage. The token efficiency is highly variable in practical. Models solving the same problem with similar accuracy can exhibit up to a \textbf{5.0$\times$} difference in token length, leading to massive gap of model reasoning ability.