List your company

Research

Benchmarks

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

309,131 benchmarksPage 1992 of 12,366

Benchmarks

TaskDatasetDomainTrendResultsLast update
Image ClassificationImageNet sub-tasks S1-S3 (10 classes)computer vision17Jun 11, 2026
General Language ModelingLiveBenchllm chat instructionnlp17Jun 9, 2026
Code GenerationLCB V2code developer ai17Jun 9, 2026
Long-video understandingLongVideoBench 0~60 mincomputer vision17Jun 9, 2026
Demand ForecastingSNBC industrial datasettabular time series17Jun 9, 2026
Dementia care dialogueDementia care dialoguellm chat instructionbio medical17Jun 9, 2026
Signal ReconstructionX-ray scattering wide-anglemiscellaneous17Jun 9, 2026
Audio Anti-spoofingASVspoof 5 (evaluation)speech audio17Jul 1, 2026
Instruction FollowingOmniCap-IF (test)llm chat instruction17Jun 9, 2026
Instructional Temporal Answer Grounding in VideoTutorialVQA (test)computer visionnlp17Jun 9, 2026
Hallucination DetectionLLM-AggreFactllm chat instructionnlp17Jun 9, 2026
Math reasoningMMLU Mathllm chat instructionnlp17Jun 9, 2026
fine-grained visual understandingMMStarcomputer vision17Jun 9, 2026
Multimodal Deep Information SeekingBrowseComp-VLretrieval search ragmultimodal17Jun 9, 2026
Long video understandingLV-Omni-Benchcomputer vision17Jun 9, 2026
Image Aesthetics AssessmentAVAcomputer vision17Jun 9, 2026
Grounded Diagnostic SegmentationDiagSegcomputer visionbio medical17Jun 8, 2026
One-to-Many Temporal GroundingOMTG Bench (test)computer visionmultimodal17Jun 5, 2026
Text-to-videoWan 2.1video generation editing17Jun 5, 2026
CTI Rule GenerationGTI (test)code developer ai17Jun 5, 2026
UI/UX selectionWiserUI-Benchcomputer vision17Jun 5, 2026
Safety EvaluationSafety Benchmarks VLG-1, VLG-2, Ch3EFadversarial safety security17Jun 5, 2026
Context-aware time-series reasoningCiK (Context-is-Key)tabular time series17Jun 5, 2026
Instructional Image EditingRE-Editimage generation editingllm chat instruction17Jun 5, 2026
Crime Density ForecastingCrime Data LA region [33.9519, 33.9951] x [-118.2635, -118.2262] 2015 (last two weeks)tabular time series17Jun 5, 2026