List your company

Research

Benchmarks

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

309,131 benchmarksPage 1995 of 12,366

Benchmarks

TaskDatasetDomainTrendResultsLast update
Health DialogueHealthBenchllm chat instructionnlp+117Jun 2, 2026
Open-ended WritingArenaHardllm chat instruction17Jun 2, 2026
Violence DetectionRWF-2000 (test)computer vision17Jul 7, 2026
Robot ManipulationRobosuite Canrobotics embodied ai17Jun 2, 2026
Robot ManipulationRobosuite Liftrobotics embodied ai17Jun 2, 2026
Generalization Bound EstimationImageNet (val)miscellaneous17Jun 2, 2026
Time-series forecastingLOBtabular time series17Jun 2, 2026
Time-series forecastingCryptotabular time series17Jun 2, 2026
System-level data generationStocktabular time series17Jun 2, 2026
System-level data generationLOBtabular time series17Jun 2, 2026
Temperature ReconstructionSubcooled Pool Boiling Task 1 (50 random snapshots)bio medicaltabular time series17Jun 2, 2026
Compositional RetrievalScanNet Apples-to-apples intersection (original & expansion compounds)retrieval search ragnlp17Jun 2, 2026
Image UnderstandingSEED-IMGcomputer visionmultimodal17Jun 2, 2026
Machine UnlearningTOFUadversarial safety security17Jun 1, 2026
Egocentric Video UnderstandingEgoSchema Subset 2023computer vision17Jun 1, 2026
3D Object DetectionnuScenes Camera View Drop 6 drops3d vision geometrycomputer vision17Jun 1, 2026
3D Object DetectionnuScenes LiDAR Object Failure rate = 0.53d vision geometrycomputer vision17Jun 1, 2026
3D Object DetectionnuScenes LiDAR Limited FOV [-60, 60]3d vision geometrycomputer vision17Jun 1, 2026
3D Object DetectionnuScenes LiDAR Drop all3d vision geometrycomputer vision17Jun 1, 2026
Object CountingCLOC (test)computer vision17Jun 1, 2026
LocomotionD4RL walker2d-medium-expert v2robotics embodied ai17Jun 16, 2026
Mechanical Drawing UnderstandingMechVQA (test)computer visionnlp17Jun 1, 2026
Knowledge Graph CompletionUMLS (test)graph17Jun 1, 2026
Knowledge Graph CompletionFamily (test)graph17Jun 1, 2026
Interpolation for continuous time dynamicsMacrophage Stimulus PCSK3 (test)tabular time series17Jun 1, 2026