General365: Benchmarking General Reasoning in Large Language Models Across Diverse and Challenging Tasks

TL;DR

General365 is a new benchmark designed to evaluate large language models' ability to perform general reasoning across diverse, challenging tasks with limited background knowledge, revealing current models' domain-dependent reasoning skills.

Contribution

The paper introduces General365, a comprehensive benchmark with 365 seed and 1,095 variant problems across eight categories to assess general reasoning in LLMs.

Findings

Top LLMs achieve only 62.8% accuracy on General365.

Current LLM reasoning skills are heavily domain-dependent.

Significant room for improvement in general reasoning abilities.

Abstract

Contemporary large language models (LLMs) have demonstrated remarkable reasoning capabilities, particularly in specialized domains like mathematics and physics. However, their ability to generalize these reasoning skills to more general and broader contexts--often termed general reasoning--remains under-explored. Unlike domain-specific reasoning, general reasoning relies less on expert knowledge but still presents formidable reasoning challenges, such as complex constraints, nested logical branches, and semantic interference. To address this gap, we introduce General365, a benchmark specifically designed to assess general reasoning in LLMs. By restricting background knowledge to a K-12 level, General365 explicitly decouples reasoning from specialized expertise. The benchmark comprises 365 seed problems and 1,095 variant problems across eight categories, ensuring both high difficulty and diversity. Evaluations across 26 leading LLMs reveal that even the top-performing model achieves only 62.8% accuracy, in stark contrast to the near-perfect performances of LLMs in math and physics benchmarks. These results suggest that the reasoning abilities of current LLMs are heavily domain-dependent, leaving significant room for improvement in broader applications. We envision General365 as a catalyst for advancing LLM reasoning beyond domain-specific tasks toward robust, general-purpose real-world scenarios. Code, Dataset, and Leaderboard: https://general365.github.io