Are Large Reasoning Models Good Everyday Reasoners? A Comparison with Non-Reasoning Models on Logical Reasoning Tasks

The paper evaluates large reasoning models (LRMs) on everyday logical reasoning tasks, introducing a benchmark that captures linguistic and pragmatic reasoning phenomena. It compares LRMs with non-reasoning models under controlled prompting and finds that LRMs often perform worse on everyday reasoning, that some non-reasoning models with chain-of-thought prompting can outperform them, and that additional prompting instructions offer limited control over reasoning behavior. These results highlight that current reasoning models do not reliably capture everyday reasoning and suggest the need for better training objectives and broader evaluation.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

• llms
• benchmarks