List your company

Research

Benchmarks

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

309,131 benchmarksPage 400 of 12,366

Benchmarks

TaskDatasetDomainTrendResultsLast update
Question AnsweringTabMWPnlp48Jun 11, 2026
Safe Reinforcement LearningSafety-Gymnasium PointPush (OSRL)robotics embodied aiadversarial safety security48Jun 9, 2026
Safe Reinforcement LearningSafety-Gymnasium AntVelocity OSRLrobotics embodied aiadversarial safety security48Jun 9, 2026
Safe Reinforcement LearningSafety-Gymnasium CarCircle OSRLrobotics embodied aiadversarial safety security48Jun 9, 2026
Safe Reinforcement LearningSafety-Gymnasium PointGoal OSRLrobotics embodied aiadversarial safety security48Jun 9, 2026
Text ClassificationAG News (Fourth Session Transition)nlp48Jun 9, 2026
Text ClassificationAG News (Second Session Transition)nlp48Jun 9, 2026
Semantic Textual SimilaritySTS (Semantic Textual Similarity) Benchmark Suitenlp48Jun 5, 2026
Adversarial Attack Transfer388 harmful behaviorsadversarial safety security48Jun 5, 2026
Image DenoisingStandard Images Foreman, Lena, House, Fingerprint, Peppers (test)computer vision48Jun 5, 2026
LLM DecodingLong Context 32Kllm chat instruction48Jun 4, 2026
Question Answering8-conceptnlp48Jun 4, 2026
Dynamic link predictionUCI (transductive)graph48Jun 4, 2026
Financial AuditingFinMRnlp48Jun 4, 2026
Financial AuditingFinancial Audit Evaluation Set 67 cases (test)nlp48Jun 4, 2026
Graph AlignmentDense Erdős-Rényi graphs (average degree 80)graph48Jun 2, 2026
Graph AlignmentSparse Erdős-Rényi graphs average degree 4graph48Jun 2, 2026
Medical Image ClassificationPATHMNISTbio medicalcomputer vision48Jun 2, 2026
RegressionCrime Incidencetabular time series48Jun 2, 2026
Non-targeted Black-box AttackMIT Places365 (val)adversarial safety security48Jun 1, 2026
Targeted Black-box Adversarial AttackPlaces365adversarial safety securitycomputer vision48Jun 1, 2026
Non-targeted Black-box Adversarial AttackPlaces365adversarial safety security48Jun 1, 2026
Two-sample testingGravitational-lensing benchmark (test)tabular time series48Jun 1, 2026
Visual Place RecognitionPittsburgh30kcomputer vision48Jun 1, 2026
Corpus Composition InferenceLLMScan Coarse-Grained 1.0 (test)llm chat instruction48May 29, 2026