List your company

Research

Benchmarks

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

309,131 benchmarksPage 1564 of 12,366

Benchmarks

TaskDatasetDomainTrendResultsLast update
Workflow Steering AttackMisinfoTask 108 constrained analytical tasksadversarial safety security20May 13, 2026
Zero-Shot Skeleton-based Action RecognitionNTU-RGB+D Xsub 120 (96/24)computer vision20May 13, 2026
Zero-Shot Skeleton-based Action RecognitionNTU-RGB+D Xsub 60 (48/12)computer vision20May 13, 2026
System IdentificationHeat Exchangertabular time series20May 13, 2026
System IdentificationMR-Dampertabular time series20May 13, 2026
System IdentificationHair Dryertabular time series20May 13, 2026
System IdentificationRobot Armtabular time series20May 13, 2026
Action RecognitionBreakfast Actions (train-test)computer vision20May 13, 2026
Named Entity RecognitionCoNLL04nlp20May 13, 2026
Deepfake AttributionDFDCcomputer visionadversarial safety security20May 13, 2026
Deepfake AttributionCeleb-DFcomputer visionadversarial safety security20May 13, 2026
Deepfake AttributionUnseen Generators Averagecomputer visionadversarial safety security20May 13, 2026
Deepfake AttributionFLUX unseencomputer visionadversarial safety security20May 13, 2026
Deepfake AttributionFLOAT unseencomputer visionadversarial safety security20May 13, 2026
Deepfake AttributionReal3DPortrait unseencomputer visionadversarial safety security20May 13, 2026
Deepfake AttributionAniTalker unseencomputer visionadversarial safety security20May 13, 2026
Deepfake AttributionEDTalk unseencomputer visionadversarial safety security20May 13, 2026
Deepfake AttributionDiffusionAct unseencomputer visionadversarial safety security20May 13, 2026
Deepfake AttributionFSRT unseencomputer visionadversarial safety security20May 13, 2026
Deepfake AttributionLIA unseencomputer visionadversarial safety security20May 13, 2026
Deepfake AttributionLivePortrait unseencomputer visionadversarial safety security20May 13, 2026
Human-Preference AlignmentMT-Benchllm chat instruction20Jun 9, 2026
Gender ClassificationCOCO 100% spurious correlationcomputer vision20May 13, 2026
Agentic Security EvaluationAgentDojo v1 (97 benign tasks, 27 injection tasks)agents tool useadversarial safety security20May 13, 2026
Visual Document ReasoningVDRcomputer visionnlp20May 12, 2026