ReasoningWeekly: A General Knowledge and Verbal Reasoning Challenge for Large Language Models
Year: 2025
Type: preprint
Abstract: Existing benchmarks for frontier models often test specialized, "PhD-level" knowledge that is difficult for non-experts to grasp. In contrast, we present a benchmark with 613 problems based on the NPR Sunday Puzzle Challenge that requires only general knowledge. Our benchmark is challenging for both humans and models; however correct solutions are easy to verify, and models' mistakes are easy to spot. As LLMs are more widely deployed in society, we believe it is useful to develop benchmarks for frontier models that humans can understand without the need for deep domain expertise. Our work reveals capability gaps that are not evident in existing benchmarks: OpenAI o1 significantly outperforms other reasoning models on our benchmark, despite being on par with other models when tested on benchmarks that test specialized knowledge. Furthermore, our analysis of reasoning outputs uncovers new kinds of failures. DeepSeek R1, for instance, often concedes with "I give up" before providing an answer that it knows is wrong. R1 can also be remarkably "uncertain" in its output and in rare cases, it does not "finish thinking," which suggests the need for techniques to ``wrap up'' before the context window limit is reached. We also quantify the effectiveness of reasoning longer to identify the point beyond which more reasoning is unlikely to improve accuracy on our benchmark.
Source: arXiv (Cornell University)
Language: English
Topic: Topic Modeling
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
Awards: G1453181110, Track 4: Advanced CI Coordination Ecosystem: Monitoring and Measurement Services, NRT-AI: Convergent, Responsible, and Ethical Artificial Intelligence Training Experience for Roboticists, G3562386289, G4010157413, ACO: An Open CI Ecosystem to Advance Scientific Discovery (OpenCI), Track 3: COre National Ecosystem for CyberinfrasTructure (CONECT), Collaborative Research: FW-HTF-RM: AI-Assisted Programming: Equipping Social and Natural Scientists for the Future of Research, Collaborative Research: FW-HTF-RM: AI-Assisted Programming: Equipping Social and Natural Scientists for the Future of Research, CAREER: Robust Perception and Customization for Long-Term Autonomous Mobile Service Robots, G5367127336, G5464919783, PRODUCTIVE AI-ASSISTED HPC SOFTWARE ECOSYSTEM, G6671297155, Track 2: Customized Multi-tier Assistance, Training, and Computational Help (MATCH) for End User ACCESS to CI
OpenAlex ID: W4407183360