List your company

ResearchFormerly WizWand

Research

Datasets

Explore the evidence bases behind AI evaluations and move from a dataset to its connected tasks and benchmarks.

78,477 datasetsPage 21 of 3,140

Dataset	Benchmarks	Papers
LAION	57	41
NYC	57	21
SimpleQA	57	63
MGSM	56	72
OCRBench	56	188
Helmholtz	56	31
REAL	56	56
Sports	56	69
VG	56	36
IHDP	56	32
Fashion	56	49
HDTF	56	60
NIAH	56	31
BigCodeBench	56	52
IPC	56	11
Clotho	55	80
RealworldQA	55	162
Counterfact	55	47
Maze2D	55	21
USPS	55	55
Youtube	55	36
Simulated data	55	22
HIV	55	59
METR-LA	55	63
PEMS-BAY	55	43