List your company

Research

Benchmarks

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

309,131 benchmarksPage 838 of 12,366

Benchmarks

TaskDatasetDomainTrendResultsLast update
Surface Normal PredictionNYU Forget set v2 (train)3d vision geometry30May 20, 2026
Depth EstimationNYU Forget set v2 (train)3d vision geometry30May 20, 2026
Semantic SegmentationNYUv2 Forget set (train)computer vision30May 20, 2026
MathematicsGSM8Knlp30Jun 30, 2026
Tool-use gatingWhen2Callagents tool use30May 20, 2026
Knowledge Base Question AnsweringCWQnlpretrieval search rag30Jun 2, 2026
Zero-shot ClassificationEvaluation Suite (ARC-e, ARC-c, PIQA, HellaS., WinoG., BoolQ) Zero-shot (test)nlpcomputer vision30May 19, 2026
Fine-grained Image HashingStanford Dogs (test)computer vision30May 19, 2026
Fine-grained Image HashingStanford Dogscomputer vision30May 19, 2026
Fine-grained Image HashingCUB200 2011 (test)computer vision30May 19, 2026
Fine-grained Image HashingCUB200 2011computer vision30May 19, 2026
Factuality EvaluationHaluEval Sum (500 items)llm chat instructionnlp30May 19, 2026
Factuality EvaluationHaluEval QA (500 items)llm chat instructionnlp30May 19, 2026
Infrared Small Target DetectionIRDSTcomputer vision30Jun 16, 2026
Binary classificationclinical breast ultrasound datasettabular time series30May 19, 2026
Image ClassificationImage Classification Datasets (val)computer vision30May 19, 2026
Natural Language UnderstandingGLUE (test)nlp30May 19, 2026
Violation DetectionPolicyGuardBenchadversarial safety security30May 20, 2026
Traffic Imputation (Sensor-kriging)METR-LAtabular time series30May 19, 2026
Traffic Imputation (Sensor-kriging)PEMS-BAYtabular time series30May 19, 2026
Traffic Imputation (Block-MAR)METR-LAtabular time series30May 19, 2026
Traffic Imputation (Block-MAR)PEMS-BAYtabular time series30May 19, 2026
Traffic Imputation (Cell-MAR)METR-LAtabular time series30May 19, 2026
Traffic Imputation (Cell-MAR)PEMS-BAYtabular time series30May 19, 2026
Image ClassificationFashion-MNISTcomputer vision30Jun 1, 2026