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
General Language Understanding	LAMBADA, ARC-C, HellaSwag, BoolQ, MMLU, GSM8K Average	nlp	56	Jun 23, 2026
Human alignment evaluation	LaMP Citation Identification, Movie Tagging, and Product Rating (test)	llm chat instructionadversarial safety security	56	Jun 16, 2026
Credit risk prediction	Real-world credit dataset	tabular time series	56	Jun 11, 2026
Motion Retargeting	Human-to-Unitree G1 Retargeting (test)	3d vision geometry	56	Jun 4, 2026
General LLM Capability	General Capability Suite MMLU, AlpacaEval, GSM8K, MATH, HumanEval