#benchmark dataset
Benchmark Dataset: 2 AI articles covering benchmark dataset news, analysis, and research
Articles
CMNIE: An Information Extraction Benchmark for Chinese Military News⭐9
CMNIE introduces a Chinese military news information extraction benchmark with 13,000 annotated instances, evaluating supervised models and LLMs on joint event,...
OpenDiscoveryTrace: A New Benchmark for Auditing the Reasoning⭐8
OpenDiscoveryTrace introduces a 558-trajectory benchmark for auditing AI scientists' reasoning, revealing process-level failures invisible to output-only evalua...