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
Multimodal tool-use	GTA	multimodalagents tool use	33	Jul 1, 2026
Psychosis detection	PSY-IAT (50 CV folds)	bio medicalcomputer vision	33	Mar 18, 2026
Reasoning	Reasoning Benchmarks GSM8K, MATH-500, AIME24, AIME25, GPQA-D	llm chat instructionnlp	33	Mar 18, 2026
Multimodal Understanding and Question Answering	Multimodal Benchmarks MME, OCRBench, DocVQA, RealWorldQA, VLMBlind	multimodalcomputer vision+1	33	Mar 18, 2026
LLM Inference	LLaMA2 7B	llm chat instruction