List your company

Research

Benchmarks

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

309,131 benchmarksPage 1948 of 12,366

Benchmarks

TaskDatasetDomainTrendResultsLast update
Multi-Robot Task AllocationLEGO-MRTA (test)robotics embodied aigraph18Feb 26, 2026
Context-aware Instruction FollowingContext-aware Instructions (test)llm chat instructionnlp18Feb 26, 2026
Text-based Person RetrievalUFine3C (evaluation)computer visionnlp18Feb 26, 2026
Instruction FollowingAlpacaEval GPT-4 (test)llm chat instruction18Apr 29, 2026
Video RepresentationUVG (test)computer vision18Feb 26, 2026
Video representationUVGcomputer vision18Feb 26, 2026
Instruction FollowingSuperNI Hold-In v1.0 (test)llm chat instruction18Feb 26, 2026
Instruction FollowingSuperNI Hold-Out v1.0 (test)llm chat instruction18Feb 26, 2026
Question AnsweringNarrativeQA No Trun. latest (test)nlp18Feb 26, 2026
Multi-modal BenchmarkMMBench Chinese (dev)multimodal18Feb 26, 2026
Scene ClassificationEuroSAT Sentinel-2 (train val)computer vision18Feb 26, 2026
Question AnsweringHotpotQA (test)nlp18Feb 26, 2026
Table-to-text GenerationLogic2Text (test)nlp18Feb 26, 2026
Image ClassificationSmall-ImageNet-127 size 32x32 and 64x64 (test)computer vision18Feb 26, 2026
Reinforcement LearningMuJoCo Humanoid v2robotics embodied ai18Feb 26, 2026
Reinforcement LearningMuJoCo Ant v2robotics embodied ai18Feb 26, 2026
Reinforcement LearningMuJoCo Walker2d v2robotics embodied ai18Feb 26, 2026
Reinforcement LearningMuJoCo Hopper v2robotics embodied ai18Feb 26, 2026
Reinforcement LearningMuJoCo HalfCheetah v2robotics embodied ai18Feb 26, 2026
Point Cloud FilteringPCNet 10K Sparse Laplace noise (synthetic)3d vision geometry18Feb 26, 2026
Point Cloud FilteringPCNet Sparse 10K3d vision geometry18Feb 26, 2026
Point Cloud FilteringPUNet Dense 50K3d vision geometry18Feb 26, 2026
Semantic SegmentationEndoVis 17computer vision18Feb 26, 2026
Interactive SegmentationCOD10Kcomputer vision18Apr 15, 2026
Region-Level CaptioningrefCOCOg (test)computer visionnlp18Feb 26, 2026