List your company

Research

Benchmarks

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

309,131 benchmarksPage 858 of 12,366

Benchmarks

TaskDatasetDomainTrendResultsLast update
Math ReasoningOlympiadllm chat instructionnlp30Mar 16, 2026
Long Video Question AnsweringVideo-MMEmultimodalcomputer vision30May 25, 2026
Multi-entity reasoning groundingME-RSRG (test)computer visionnlp30Mar 16, 2026
Goal-reaching PlanningPointMaze Medium Long-Horizon (50 steps)robotics embodied ai30Mar 13, 2026
Medical Question AnsweringPolish Board Certification Examinationsbio medicalnlp30Mar 13, 2026
Large-scale Sparse Multi-objective OptimizationSMOP8miscellaneous30Mar 13, 2026
Large-scale Sparse Multi-objective OptimizationSMOP7miscellaneous30Mar 13, 2026
Large-scale Sparse Multi-objective OptimizationSMOP6miscellaneous30Mar 13, 2026
Large-scale Sparse Multi-objective OptimizationSMOP5miscellaneous30Mar 13, 2026
Large-scale Sparse Multi-objective OptimizationSMOP4miscellaneous30Mar 13, 2026
Large-scale Sparse Multi-objective OptimizationSMOP3miscellaneous30Mar 13, 2026
Anomaly DetectionGrid Loss D4 (test)tabular time series30Mar 13, 2026
Poisoning AttackMuSiQueadversarial safety security30Mar 13, 2026
Poisoning AttackGraph-Medicaladversarial safety security30Mar 13, 2026
Poisoning AttackGraph-Storyadversarial safety security30Mar 13, 2026
Multi-view 3D ReconstructionT&T (test)3d vision geometry30Mar 13, 2026
Multi-view 3D ReconstructionETH3D (test)3d vision geometry30Mar 13, 2026
Multi-view 3D ReconstructionScanNet++ (test)3d vision geometry30Mar 13, 2026
Text-to-image reward alignmentGenEval (test)image generation editingllm chat instruction30Mar 13, 2026
Method ranking self-consistencyCombined benchmark M=120 questionsllm chat instructionnlp30Mar 12, 2026
Image Captioning HallucinationMSCOCO 500 images (val)computer visionnlp30Mar 12, 2026
Structure-from-MotionDTU3d vision geometrycomputer vision30Mar 12, 2026
ClassificationADHD-200 (test)computer visionnlp+330Jun 30, 2026
PSDexHand PSrobotics embodied ai30Mar 12, 2026
Machine UnlearningTOFU (Forget01)adversarial safety security30Jun 12, 2026