error patterns
- ErrorTrace: A Black-Box Traceability Mechanism Based on Model Family Error Space
- OST-Bench: Evaluating the Capabilities of MLLMs in Online Spatio-temporal Scene Understanding
- QCircuitBench: A Large-Scale Dataset for Benchmarking Quantum Algorithm Design
- ResearchCodeBench: Benchmarking LLMs on Implementing Novel Machine Learning Research Code
- SolidGeo: Measuring Multimodal Spatial Math Reasoning in Solid Geometry