List your company

Research

Benchmarks

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

309,131 benchmarksPage 1508 of 12,366

Benchmarks

TaskDatasetDomainTrendResultsLast update
Question AnsweringSQuADShifts 1.0 (test)nlp21Feb 26, 2026
Summarization EvaluationSummEval 1.0 (test)nlp21Feb 26, 2026
Machine TranslationMSCOCO En-Frnlp21Jun 16, 2026
Machine TranslationWMT newstest 2010 (test)nlp21Feb 26, 2026
Document Layout AnalysisDocLayNet (test)computer vision21Apr 28, 2026
Machine TranslationFR-ENnlp21Feb 26, 2026
Novel View SynthesisSynthetic 360° scenes Blender (test)3d vision geometry21Feb 26, 2026
Extractive Question AnsweringMolweni (test)nlp21May 29, 2026
Instruction FollowingVicuna benchmark zero-shotllm chat instruction21Feb 26, 2026
Multimodal classificationN24News (test)multimodalcomputer vision+121Feb 26, 2026
Semantic SegmentationCityscapes (val)computer vision21Feb 26, 2026
Point cloud registrationLoKITTI3d vision geometry21Feb 26, 2026
Object DetectionClipart1k 1.0 (test)computer vision21Feb 26, 2026
Vision-and-Language NavigationRxR seen (val)robotics embodied aimultimodal21Feb 26, 2026
Pedestrian DetectionCityPersons 1.0 (val)computer vision21Feb 26, 2026
Image RetrievalGLD v2retrieval search ragcomputer vision21Mar 31, 2026
Visual LocalizationCambridge Landmarks ShopFacadecomputer vision3d vision geometry21Apr 8, 2026
Image GenerationImageNet 64x64 (train)image generation editing21Apr 27, 2026
Video Anomaly DetectionAvenue classic (test)computer vision21Feb 26, 2026
Generalized Category DiscoveryImageNet-100 (test)computer vision21Feb 26, 2026
3D Face ReconstructionREALY3d vision geometrycomputer vision21Jun 29, 2026
Text-to-image generationMS-COCO zero-shot FID-30k 256x256image generation editing21Feb 26, 2026
Video Action ClassificationK400 time-correlated (val)computer vision21Feb 26, 2026
Video Action ClassificationSSv2 time-correlated (val)computer vision21Feb 26, 2026
Video Action ClassificationUCF101 time-correlated (val)computer vision21Feb 26, 2026