NPHardEval 榜单发布:基于复杂度类评估 LLM 推理能力

原标题:NPHardEval Leaderboard: Unveiling the Reasoning Abilities of Large Language Models through Complexity Classes and Dynamic Updates
45AI 研判分

NPHardEval 推出新基准测试,利用计算复杂性理论(如 NP-Hard)动态评估大语言模型的推理极限。该榜单旨在通过引入动态更新机制,解决传统静态基准易被过拟合的问题,提供更真实的模型能力画像。

报道正文

NPHardEval Leaderboard: Unveiling the Reasoning Abilities of Large Language Models through Complexity Classes and Dynamic Updates