We introduce LLM-Wikirace, a benchmark for evaluating planning, reasoning, and world knowledge in large language models (LLMs). In LLM-Wikirace, models must efficiently navigate Wikipedia hyperlinks step by step to reach a target page from a given source, requiring look-ahead planning and the ability to reason about how concepts are connected in the real world. We evaluate a broad set of open- and closed-source models, including Gemini-3, GPT-5, and Claude Opus 4.5, which achieve the strongest results on the easy level of the task and demonstrate superhuman performance. Despite this, performance drops sharply on hard difficulty: the best-performing model, Gemini-3, succeeds in only 23\% of hard games, highlighting substantial remaining challenges for frontier models. Our analysis shows that world knowledge is a necessary ingredient for success, but only up to a point, beyond this threshold, planning and long-horizon reasoning capabilities become the dominant factors. Trajectory-level analysis further reveals that even the strongest models struggle to replan after failure, frequently entering loops rather than recovering. LLM-Wikirace is a simple benchmark that reveals clear limitations in current reasoning systems, offering an open arena where planning-capable LLMs still have much to prove. Our code and leaderboard available at https:/llmwikirace.github.io.

翻译：我们提出了LLM-Wikirace，一个用于评估大语言模型（LLMs）规划、推理与世界知识能力的基准。在LLM-Wikirace中，模型必须通过维基百科超链接逐步高效地从给定源页面导航至目标页面，这需要前瞻性规划以及推理现实世界中概念如何连接的能力。我们评估了广泛的开源与闭源模型，包括Gemini-3、GPT-5和Claude Opus 4.5，这些模型在任务的简单难度上取得了最佳结果，并展现出超越人类的表现。尽管如此，在困难难度上性能急剧下降：表现最佳的模型Gemini-3仅在23%的困难游戏中成功，突显了前沿模型仍面临的重大挑战。我们的分析表明，世界知识是成功的必要因素，但仅在一定程度内；超过此阈值后，规划与长视野推理能力成为主导因素。轨迹级分析进一步揭示，即使是最强的模型在失败后也难以重新规划，经常陷入循环而非恢复。LLM-Wikirace是一个简单的基准，它揭示了当前推理系统存在的明显局限，为具备规划能力的LLMs提供了一个仍需大量证明的开放竞技场。我们的代码与排行榜可在 https:/llmwikirace.github.io 获取。