List your company

Research

Benchmarks

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

309,131 benchmarksPage 643 of 12,366

Benchmarks

TaskDatasetDomainTrendResultsLast update
Class-Incremental LearningClass-Incremental Learning Sequences Easycomputer visiontabular time series36Mar 5, 2026
Class-Incremental LearningClass-Incremental Learning Sequences Hardcomputer visiontabular time series36Mar 5, 2026
Mathematical ReasoningMinervaMathllm chat instructionnlp36Apr 20, 2026
Scientific Code GenerationSciCode (test)code developer ai36Mar 4, 2026
Speaker Impersonation AttackVoxCeleb1 and CNCeleb subsampled (test-enrollment)speech audioadversarial safety security36Mar 4, 2026
Satellite→Drone Geo-localizationSUES-200 250mcomputer vision36Mar 17, 2026
Satellite→Drone Geo-localizationSUES-200 200mcomputer vision36Mar 17, 2026
Harmful RefusalWG (test)adversarial safety security36Jul 7, 2026
Mean Performance EvaluationDownstream Tasks Summarymiscellaneous36Mar 4, 2026
Language ModelingLambada Standardnlp36Mar 4, 2026
Multivariate Time Series ClassificationSelfRegulationSCP2 UEA (test)tabular time series36Jul 7, 2026
Watermark DetectionC4adversarial safety security36Mar 4, 2026
Instruction FollowingUnNI (test)llm chat instruction36Mar 4, 2026
Instruction FollowingSuper-NI (test)llm chat instruction36Mar 4, 2026
Instruction FollowingVicuna Eval (test)llm chat instruction36Mar 4, 2026
Multi-hop QA RetrievalMuSiQueretrieval search ragnlp36Mar 17, 2026
Genomic PredictionSoybeanbio medical36Mar 4, 2026
Graph OOD DetectionIMDB-M IMDB-Bgraph36Apr 1, 2026
ClassificationTeacher Education Dataset DT 1.0 (test)computer visionnlp+336Mar 4, 2026
Out-of-Distribution DetectionImageNetcomputer visiontabular time series36May 13, 2026
CausalityQRDatamiscellaneous36Mar 4, 2026
Question AnsweringARC-Enlp36Feb 27, 2026
Question AnsweringARC Challengenlp36Feb 27, 2026
3D ReconstructionReplica3d vision geometry36Feb 27, 2026
Rent's parameter estimationArtificial and Real Netlists jpeg, nova, netcard, tate_pairing, CA53, ariane-133 v1 (test)miscellaneous36Feb 27, 2026