I have authored three papers that offer a thorough analysis of the logical reasoning capabilities of large language models (LLMs)

[Mihir3009]

Please add these papers to your list if you see fit.

1. LogicBench: Towards Systematic Evaluation of Logical Reasoning Ability of Large Language Models
2. Multi-LogiEval: Towards Evaluating Multi-Step Logical Reasoning Ability of Large Language Models
   
3. Step-by-Step Reasoning to Solve Grid Puzzles: Where do LLMs Falter?

Thanks,
Mihir Parmar.