List your company

Research

Benchmarks

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

309,131 benchmarksPage 1481 of 12,366

Benchmarks

TaskDatasetDomainTrendResultsLast update
De novo 3D molecule generationQM9bio medical3d vision geometry21Jun 15, 2026
Offline Reinforcement LearningWalker2drobotics embodied ai21Feb 26, 2026
Text ClassificationRCV1 v2 (train)nlp21Feb 26, 2026
Text ClassificationRCV1 v2 (val)nlp21Feb 26, 2026
Zero-shot Question Answering and ReasoningEvaluation Suite Zero-shot (ARC, LogiQA, Wino, CSQA, BoolQ, PIQA, MMLU)nlpllm chat instruction21Feb 26, 2026
Fraud DetectionIEEE-CIStabular time series21Jun 9, 2026
Mathematical ReasoningAMCllm chat instructionnlp21Feb 26, 2026
EEG-based Emotion RecognitionSEEDbio medicalspeech audio21Feb 26, 2026
Deterministic forecastingSolar TSFM-Benchtabular time series21Feb 27, 2026
Deterministic forecastingETT Avg TSFM-Benchtabular time series21Feb 27, 2026
Speaker DiarizationCallHome 2-spks with 0.25s collar tolerance (test)speech audio21Feb 26, 2026
Commonsense ReasoningWinoGrande 0-shot (test)nlp21Jun 26, 2026
QoS PredictionWSDREAM Response Time 2T (test)tabular time series21Feb 26, 2026
Cell type classificationCOVID-PBMC celltype5 (test)bio medical21Feb 26, 2026
Missing Data ImputationExchange (test)tabular time series21Feb 26, 2026
Vehicle Routing ProblemCVRP n=50miscellaneous21May 1, 2026
Outlier DetectionWilttabular time series21Mar 17, 2026
Out-of-Distribution DetectionPlaces365computer visiontabular time series21Apr 7, 2026
Intrusion DetectionTON_IoTtabular time series21Jun 23, 2026
Multimodal ClassificationUKBmultimodalcomputer vision+121Feb 26, 2026
Natural Language UnderstandingGLUE original (val)nlp21May 13, 2026
Rubric satisfaction evaluationMedicalllm chat instruction21Feb 26, 2026
Rubric satisfaction evaluationArXivllm chat instruction21Feb 26, 2026
Node classificationCoraMLgraph21Jun 12, 2026
Delivery Decision Policy EvaluationSynthetic Urban Service Regionrobotics embodied aitabular time series21Feb 26, 2026