List your company

Research

Benchmarks

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

309,131 benchmarksPage 862 of 12,366

Benchmarks

TaskDatasetDomainTrendResultsLast update
Combinatorial ReasoningGraph Coloringgraphnlp30May 26, 2026
Image ClassificationCIFAR-100computer vision30Mar 4, 2026
RetrosynthesisUSPTO-50k Without Reaction Typebio medical30Mar 4, 2026
Stability PredictionMatbench-Discovery unique structure prototypesbio medical30May 21, 2026
Point Cloud CompletionRabbit point cloud3d vision geometry30Mar 17, 2026
Point Cloud CompletionMario point cloud3d vision geometry30Mar 17, 2026
Point Cloud CompletionFrog point cloud3d vision geometry30Mar 17, 2026
Remote Sensing Image Dehazing (RSI Dehazing)RICE1computer vision30Apr 6, 2026
Jailbreak RobustnessStrongRejectadversarial safety security30May 20, 2026
CopyCopy OOD lengths: 2x, 4x, 8x, 16x, 32x, 64xllm chat instruction30Mar 4, 2026
MQMTARMQMTAR OOD lengths 2x 4x 16x 64x 256x 1024xnlp30Mar 4, 2026
Multiple Instance Learning ClassificationTIGERtabular time series30Jun 5, 2026
Multiple Instance Learning ClassificationFOXtabular time series30Jun 5, 2026
Mobility PredictionSPBtabular time series30Mar 4, 2026
Mobility PredictionMOWtabular time series30Mar 4, 2026
Mobility PredictionMAOtabular time series30Mar 4, 2026
Mobility PredictionKLP Foursquare Gowalla (test)tabular time series30Mar 4, 2026
Mobility PredictionJKT Foursquare Gowalla (test)tabular time series30Mar 4, 2026
Identification of inactive attention headsWinoGrandenlpadversarial safety security30Mar 4, 2026
Document Question AnsweringLongDocURLnlpcomputer vision30Apr 13, 2026
OOD detectionMVTec Metal Nut - Similar artifactscomputer visiontabular time series30Feb 27, 2026
OOD DetectionMVTec Metal Nut (Similar)computer visiontabular time series30Feb 27, 2026
Video Super-ResolutionVid4 Y (test)video generation editingcomputer vision30Feb 27, 2026
Multimodal ClassificationKinetics-Sounds (test)multimodalcomputer vision+130Apr 8, 2026
Handwriting RetrievalHandwriting Spanish synthetic disjoint fonts (Out-of-Domain (OOD))computer visionnlp30Feb 27, 2026