List your company

Research

Benchmarks

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

309,131 benchmarksPage 1052 of 12,366

Benchmarks

TaskDatasetDomainTrendResultsLast update
Skill executionSkillsBenchagents tool usecode developer ai+126Jun 2, 2026
Nudity erasureMMA-Diff tar 1.5 (test)image generation editingadversarial safety security26May 12, 2026
Face Forgery DetectionGenFace AMcomputer vision26May 12, 2026
Code generationMBPPcode developer ai26Jun 30, 2026
3D Object ExtractionLLFF3d vision geometrycomputer vision26May 12, 2026
3D Object ExtractionLeRF3d vision geometrycomputer vision26May 12, 2026
3D Object ExtractionMip-NeRF 3603d vision geometrycomputer vision26May 12, 2026
Class-incremental image classificationCUB-200computer vision26Jun 5, 2026
Multimodal ReasoningMathVersemultimodalnlp26May 12, 2026
Multimodal ReasoningMathVisionmultimodalnlp26May 12, 2026
Mathematical ReasoningMATH lightevalllm chat instructionnlp26May 26, 2026
Triplet AccuracyDeliberation Evaluation Suite GSC, Remesh, Polis (test)nlp26May 12, 2026
Computer Vision ReasoningCV-Benchcomputer visionllm chat instruction26May 26, 2026
Anomaly DetectionADBench MNIST-Ctabular time series26May 11, 2026
Anomaly DetectionADBench breastwtabular time series26May 11, 2026
Anomaly DetectionADBench aloitabular time series26May 11, 2026
Graph ExpressivityBRECgraph26May 25, 2026
Tool UseToolAlpacaagents tool use26May 13, 2026
Interaction RecognitionImageNet-1k 4 objectscomputer vision26May 8, 2026
Interaction RecognitionImageNet 1k (3 objects)computer vision26May 8, 2026
Interaction RecognitionImageNet-1k 2 objectscomputer vision26May 8, 2026
Interaction RecognitionImageNet-1k 1 objectcomputer vision26May 8, 2026
ClassificationMNIST-SVHN r=100computer visionnlp+326May 8, 2026
ClassificationMNIST-SVHN r=20computer visionnlp+326May 8, 2026
ClassificationMNIST-SVHN r=10computer visionnlp+326May 8, 2026