Benchmarks

Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.

309,131 indexed

Task	Dataset	Domain	Results	Last Update
Open-book Question Answering	OpenBookQA 1.0 (test)	nlpretrieval search rag	33	Feb 26, 2026
Yes/No Reading Comprehension	BoolQ 1.0 (test)	nlpllm chat instruction	33	Feb 26, 2026
Multiple-choice Question Answering	Bangla MMLU 1.0 (test)	nlp	33	Feb 26, 2026
Knowledge Graph Retrieval	Prime (test)	retrieval search raggraph	33	May 29, 2026
Knowledge Graph Retrieval	MAG (test)	retrieval search raggraph