List your company

Research

Benchmarks

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

309,131 benchmarksPage 2151 of 12,366

Benchmarks

TaskDatasetDomainTrendResultsLast update
Embodied ManipulationEB-Manipulationrobotics embodied ai16May 27, 2026
Mathematical ReasoningPolaris (test)llm chat instructionnlp16May 27, 2026
Adversarial AttackVQA v2 (test)adversarial safety securitycomputer vision16May 27, 2026
Adversarial AttackDALLE-3adversarial safety securitycomputer vision16May 27, 2026
Note-table consistency verificationEHRCon Nursing notesbio medicalnlp16May 27, 2026
Note-table consistency verificationEHRCon Physician notesbio medicalnlp16May 27, 2026
Note-table consistency verificationEHRCon Discharge notesbio medicalnlp16May 27, 2026
Toxicity UnlearningToxicityadversarial safety securitynlp16May 27, 2026
Dangerous Knowledge UnlearningWMDPadversarial safety securityllm chat instruction16May 27, 2026
Novel View SynthesisOmniUW synthetic (rocks)3d vision geometry16May 27, 2026
Novel View SynthesisOmniUW synthetic (pool)3d vision geometry16May 27, 2026
Novel View SynthesisOmniUW synthetic (deepsea)3d vision geometry16May 27, 2026
Novel View SynthesisOmniUW synthetic (building)3d vision geometry16May 27, 2026
Video Temporal GroundingActivityNet Captioncomputer visionnlp16May 27, 2026
Reasoning-based RetrievalBRIGHT 1.0 (test)retrieval search ragnlp16May 27, 2026
Zero-shot EvaluationLM Evaluation Harness PIQA, HellaSwag, COPA, RTE, OpenBookQA, LAMBADA-OpenAInlpllm chat instruction16May 27, 2026
Trajectory predictionSwiss roundabout (val)robotics embodied aitabular time series16May 27, 2026
General Reasoning and KnowledgeAggregate BBH, MMLU, ARC-C, ThmQAllm chat instruction16May 27, 2026
Constrained Location Routing ProblemCLRP10 Syntheticmiscellaneous16May 27, 2026
Video Spatial ReasoningSpaceVista-Benchcomputer visionmultimodal16May 27, 2026
Visual Object TrackingFE 240hzcomputer vision16May 27, 2026
Text RemovalSCUT-EnsTextcomputer vision16May 27, 2026
Contamination Detection187 datasets across 6 TSFMsbio medical16May 27, 2026
Visual ReconstructionImageNet-1K (val)computer vision16May 26, 2026
ClassificationLSM held-out patches (test)computer visionnlp+316May 26, 2026