List your company

Research

Benchmarks

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

309,131 benchmarksPage 805 of 12,366

Benchmarks

TaskDatasetDomainTrendResultsLast update
UnlearningGoodreads-NCadversarial safety security31May 6, 2026
Mitochondria SegmentationEPFL → MitoEM-R (test)computer visionbio medical31May 4, 2026
ClassificationFlood Risk in India Standard (5-fold CV)computer visionnlp+331May 1, 2026
ClassificationCrop Mapping 3000-sample subsample Standard (5-fold CV)computer visionnlp+331May 1, 2026
ClassificationWilt Standard (5-fold CV)computer visionnlp+331May 1, 2026
ClassificationUrban Land Cover Standard (5-fold CV)computer visionnlp+331May 1, 2026
Visual Question AnsweringVizWizmultimodalcomputer vision+131Jun 1, 2026
Agent Task Completionτ-bench-retailagents tool use31Jun 4, 2026
Long-Video Question AnsweringLVBenchmultimodalcomputer vision31Jun 23, 2026
Graph ReconstructionCiteSeergraph31Apr 24, 2026
Multimodal EmbeddingMMEB V1multimodalnlp+131Jun 12, 2026
Interactive Environment Task CompletionALFWorld (Unseen)robotics embodied aiagents tool use31May 19, 2026
Interactive Environment Task CompletionALFWorld (Seen)robotics embodied aiagents tool use31May 19, 2026
Rejection Accuracy EvaluationAverage across all datasets (test)miscellaneous31Apr 21, 2026
Logical ReasoningGame-of-24nlp31Apr 21, 2026
Science and Engineering Question AnsweringTheoremQAnlpllm chat instruction31Apr 21, 2026
Mathematical ReasoningGSM8Kllm chat instructionnlp31Apr 21, 2026
Nonlinear DeblurringImageNet 256 × 256computer vision31Jun 30, 2026
Commonsense ReasoningCommonsense Reasoning (test)nlp31Jul 2, 2026
Camouflaged Object DetectionNC4Kcomputer vision31Apr 21, 2026
Semantic SegmentationOVRSISBench V2computer vision31Apr 20, 2026
Open-World Knowledge Graph Question AnsweringGLOW-Bench RH 2retrieval search raggraph+131Apr 16, 2026
Open-World Knowledge Graph Question Answeringogbn-productretrieval search raggraph+131Apr 16, 2026
Genomic ClassificationGERMbio medical31Apr 16, 2026
Web BrowsingBrowseComp-Plusagents tool use31Jun 12, 2026