List your company

Research

Benchmarks

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

309,131 benchmarksPage 670 of 12,366

Benchmarks

TaskDatasetDomainTrendResultsLast update
Text generationMasked DFM backbone 1024 samplesnlp35Jun 24, 2026
Medical Image ClassificationMedical Image Classification 10 datasets avgbio medicalcomputer vision35Jun 23, 2026
Image ClassificationCIFAR-100-LT extreme (R-100) (test)computer vision35Jun 23, 2026
Image ClassificationCIFAR-100-LT mild (R-10) (test)computer vision35Jun 23, 2026
Image ClassificationCIFAR-100computer vision35Jun 23, 2026
Image ClassificationCIFAR-10computer vision35Jun 23, 2026
Operator Learning Rollout PredictionAllen-Cahn Equation E2tabular time series35Jun 23, 2026
Pick and PlaceSim: Pick and Place Image v1 (evaluation)robotics embodied ai35Jun 23, 2026
Block PushSim: Block Push Image v1 (test)robotics embodied ai35Jun 23, 2026
Block PushSim: Block Push State v1 (evaluation)robotics embodied ai35Jun 23, 2026
UWB localizationRandom walk experiment (Cluttered)3d vision geometry35Jun 19, 2026
Open-Vocabulary Semantic SegmentationORAD-3Dcomputer vision35Jun 18, 2026
Open-domain long-horizon evaluationFRAMES (test)llm chat instruction35Jun 16, 2026
Open-domain long-horizon evaluationBrowseComp-Plus (BCP) (test)llm chat instruction35Jun 16, 2026
Zero-shot Question AnsweringEvaluation Suite (WinoGrande, PiQA, HellaSwag, ARC-E, ARC-C) Zero-shotnlpllm chat instruction35Jun 15, 2026
Language-conditioned Manipulation PlanningVLABenchrobotics embodied ainlp35Jun 11, 2026
ClassificationAdultcomputer visionnlp+335Jun 11, 2026
Image ClassificationFashion MNISTcomputer vision35Jun 11, 2026
Network Transmission Performance EvaluationWireless Link RELIABLE QoStabular time series35Jun 11, 2026
Network Transmission Performance EvaluationWireless Link BEST_EFFORT QoStabular time series35Jun 11, 2026
Network Transmission Performance EvaluationWired Link RELIABLE QoStabular time series35Jun 11, 2026
Network Transmission Performance EvaluationWired Link BEST_EFFORT QoStabular time series35Jun 11, 2026
Optical ReasoningAquaRat, Gsm8k, GPQA Diamond, ScienceQA, Zebra-Cot (test)computer visionnlp35Jun 9, 2026
Image ClassificationImageNet-C Severity 3 1.0computer vision35Jul 2, 2026
Jailbreak RobustnessJBBadversarial safety security35Jun 5, 2026