List your company

Research

Benchmarks

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

309,131 benchmarksPage 555 of 12,366

Benchmarks

TaskDatasetDomainTrendResultsLast update
Mathematical ReasoningOlympiadBench (test)llm chat instructionnlp40Jun 1, 2026
Motion Sequence InterpolationLaFAN13d vision geometry40Feb 26, 2026
Motion Sequence InterpolationHumanML3D3d vision geometry40Feb 26, 2026
Deepfake DetectionFF++ video-level 8 (test)computer visionadversarial safety security40Feb 26, 2026
Reasoning SegmentationReasonSeg long (test)computer vision40Feb 26, 2026
Reasoning SegmentationReasonSeg short (test)computer vision40Feb 26, 2026
AI-generated image detectionCelebA-HQ v2 (test)image generation editingcomputer vision40Feb 26, 2026
Vehicle Re-IdentificationRGBNT100computer vision40May 12, 2026
Land-cover classificationEuroSATcomputer vision40Jun 23, 2026
Audio-visual NavigationMatterport3D Heardrobotics embodied aispeech audio+140Apr 8, 2026
Audio-visual NavigationReplica Heardrobotics embodied aispeech audio+140Apr 8, 2026
Face Forgery DetectionCDF v1computer vision40Mar 4, 2026
Streaming Video UnderstandingRVS-Moviecomputer vision40Jun 19, 2026
Text Image Super-ResolutionReal-CE (val)computer visionimage generation editing40May 14, 2026
Deepfake DetectionCeleb-DF (test)computer visionadversarial safety security40Mar 17, 2026
Text-to-Image GenerationDrawBenchimage generation editing40Feb 26, 2026
Compositional Hallucination EvaluationOmniVCHall Averagemultimodalnlp40Feb 26, 2026
Compositional Hallucination EvaluationOmniVCHall Generatedmultimodalnlp40Feb 26, 2026
Compositional Hallucination EvaluationOmniVCHall Realmultimodalnlp40Feb 26, 2026
Out-of-scope refusalScienceQA out-of-scope (test)llm chat instructionadversarial safety security40Feb 26, 2026
Survival AnalysisTCGA-LUAD (test)tabular time series40May 21, 2026
4D GenerationConsistent4Dvideo generation editing40Jun 2, 2026
Human Preference EvaluationImageRewardllm chat instruction40Apr 21, 2026
Counterfactual ReasoningCVQAnlp40Feb 27, 2026
Art Style ErasureArtist style and content prompts 5 groups SD v1.4 based (test)image generation editing40Feb 26, 2026