List your company

Research

Benchmarks

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

309,131 benchmarksPage 697 of 12,366

Benchmarks

TaskDatasetDomainTrendResultsLast update
Semantic SegmentationADE20K 150 classes (val)computer vision35Feb 27, 2026
Anomaly DetectionMVTec ADtabular time series35Mar 17, 2026
Mathematical ReasoningMATH500llm chat instructionnlp34Jul 7, 2026
Tabular Classification and RegressionTextTabtabular time series34Jun 30, 2026
Gene-expression classificationCUMIDA-42 RF-100 feature arm v2 (3 seeds x 3 folds)bio medicaltabular time series34Jun 30, 2026
ClassificationCUMIDA-42 RF-25 + 75 random feature arm v1 (test)computer visionnlp+334Jun 30, 2026
Security violation detection31 user-space programs (aggregated results across programs)adversarial safety security34Jun 30, 2026
Provenance TracingVQDiffadversarial safety security34Jun 30, 2026
Multiframe Infrared Small Target DetectionTSIRMT Hardcomputer vision34Jun 29, 2026
Multiframe Infrared Small Target DetectionTSIRMT (All)computer vision34Jun 29, 2026
Multi-modal UnderstandingMMMUmultimodal34Jun 26, 2026
Optimization Modeling and SolvingNLP4LPmiscellaneous34Jul 7, 2026
Question AnsweringLLAMA 1nlp34Jun 24, 2026
Question AnsweringSimpleQAnlp34Jun 24, 2026
Visual Object TrackingNfScomputer vision34Jul 3, 2026
Visual Spatial InstructionVSI-Benchcomputer visionnlp34Jun 19, 2026
Image GenerationImageNet 50Kimage generation editing34Jun 19, 2026
Agentic terminal task resolutionTerminal-Bench 2agents tool usecode developer ai34Jun 17, 2026
Geometric PerceptionGePBench 1.0 (Overall)3d vision geometrycomputer vision34Jun 16, 2026
Geometric PerceptionGePBench 1.0 (Hard)3d vision geometrycomputer vision34Jun 16, 2026
Geometric PerceptionGePBench Easy 1.03d vision geometrycomputer vision34Jun 16, 2026
Offline Multi-Objective OptimizationOff-MOO-Bench Sci-Designmiscellaneous34Jun 16, 2026
Offline Multi-Objective OptimizationOff-MOO-Bench MO-NASmiscellaneous34Jun 16, 2026
Protein-ligand binding affinity predictionATOM3D LBA 30% sequence identitybio medical34Jun 15, 2026
Image ClassificationBloodMNIST (test)computer vision34Jul 9, 2026