List your company

Research

Benchmarks

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

309,131 benchmarksPage 1782 of 12,366

Benchmarks

TaskDatasetDomainTrendResultsLast update
Protein fitness predictionProteinGymbio medical19Feb 26, 2026
Dual-target drug design12,917 pairs of targets dual-target setting (test)bio medical19May 26, 2026
Tile-level classificationPCam (test)computer vision19Feb 26, 2026
Continuous ControlD4RL Walker2d mediumrobotics embodied ai19Jun 9, 2026
Global OptimizationType U various geometries syntheticmiscellaneous19Feb 26, 2026
Per time-step regressionWalker2Dtabular time series19Feb 26, 2026
Global OptimizationF6 benchmark functionmiscellaneous19Jun 4, 2026
Graph ClassificationRDT-B (test)graph19Feb 26, 2026
Word-level predictionPTB word-level (test)nlp19Feb 26, 2026
Time Series ClassificationCMUSUBJECT16 (test)tabular time series19Feb 26, 2026
Image ClassificationMNIST-10 (test)computer vision19Feb 26, 2026
Material generationMP-20 (test)bio medical19May 12, 2026
Force predictionMD17 revised (test)bio medicaltabular time series19Feb 26, 2026
Jet TaggingQuark-Gluon Tagging (test)bio medical19May 19, 2026
RegressionFreeSolv (scaffold)tabular time series19Feb 26, 2026
Molecular energy predictionQM9bio medicalgraph19Feb 26, 2026
Graph RetrievalFM (test)graphretrieval search rag19Feb 26, 2026
User-Generated Content Video Quality AssessmentYouTube-UGC original (test)video generation editingcomputer vision19Feb 26, 2026
PansharpeningWorldView-2 reduced-resolution 256 × 256 subscenecomputer vision19Feb 26, 2026
Real-world UnderstandingR-Benchcomputer visionmultimodal19Feb 27, 2026
3D Object ClassificationScanObjectNN OBJ_ONLY v13d vision geometrycomputer vision19Feb 26, 2026
Reflective Object ReconstructionGlossy Synthetic3d vision geometrycomputer vision19Mar 31, 2026
CUA classification3D uterine ultrasound datasetbio medicalcomputer vision19Feb 26, 2026
Long-form Question AnsweringASQAllm chat instructionnlp19Apr 10, 2026
Semantic SegmentationPST900 (evaluation)computer vision19Feb 26, 2026