List your company

Research

Benchmarks

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

309,131 benchmarksPage 1598 of 12,366

Benchmarks

TaskDatasetDomainTrendResultsLast update
Dual-arm ManipulationRoboTwin Medium Horizon Tasks 150-230 Steps 2.0robotics embodied ai20May 20, 2026
Dual-arm ManipulationRoboTwin Short Horizon Tasks 100-130 Steps 2.0robotics embodied ai20May 20, 2026
Anomaly Detectionbreastw In-Domaintabular time series20Mar 17, 2026
Commonsense ReasoningCommonsense Reasoning Suite LM Eval Harnessnlp20Apr 21, 2026
Novel-view reconstructionHyperNeRF 4D LangSplat (test)3d vision geometrycomputer vision20Mar 17, 2026
Novel-view reconstructionHyperNeRF held-out 4D LangSplat (test)3d vision geometrycomputer vision20Mar 17, 2026
Visual Question AnsweringMathVistamultimodalcomputer vision+120May 12, 2026
Structured OCRORB-En-SROIE Rotated 4-classcomputer vision20Mar 17, 2026
Faithfulness EvaluationHalogennlp20Mar 17, 2026
Monocular Depth EstimationScanNet++ (test)3d vision geometrycomputer vision20Mar 23, 2026
LVEF estimationEchoNet-Dynamic (test)bio medicalcomputer vision20Mar 30, 2026
Agent Behavior EvaluationSocial Simulation Family context 1.0agents tool usellm chat instruction20Mar 17, 2026
Agent Behavior EvaluationSocial Simulation Workplace context 1.0agents tool usellm chat instruction20Mar 17, 2026
Agent Behavior EvaluationSocial Simulation School context 1.0agents tool usellm chat instruction20Mar 17, 2026
Multi-hop Question AnsweringBamboogle standard (val)nlpretrieval search rag20Mar 17, 2026
Jailbreak AttackGrok 4adversarial safety security20Mar 17, 2026
Jailbreak AttackGLM-4-Airadversarial safety security20Mar 17, 2026
Jailbreak AttackDeepSeekadversarial safety security20Mar 17, 2026
Jailbreak AttackMistral-7Badversarial safety security20Mar 17, 2026
Jailbreak AttackQwen2.5-7Badversarial safety security20Mar 17, 2026
Jailbreak AttackGemma 4B 3adversarial safety security20Mar 17, 2026
Jailbreak AttackLlama 8B 3.1adversarial safety security20Mar 17, 2026
MRI ReconstructionHCP (Human Connectome Project) single-coil T1-weighted (test)bio medicalcomputer vision20Mar 17, 2026
Planar Surface ReconstructionPlanar Surface3d vision geometry20Mar 17, 2026
Spherical Surface Reconstruction50mm Sphere3d vision geometry20Mar 17, 2026