List your company

Research

Benchmarks

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

309,131 benchmarksPage 2164 of 12,366

Benchmarks

TaskDatasetDomainTrendResultsLast update
Machine UnlearningMUSE forget-setadversarial safety security16May 15, 2026
Knowledge RetentionWMDP cyber (retain)llm chat instruction16May 15, 2026
Machine UnlearningWMDP-cyber forget-setadversarial safety security16May 15, 2026
Knowledge RetentionWMDP-chem (retain)llm chat instruction16May 15, 2026
Machine UnlearningWMDP chem forget-setadversarial safety security16May 15, 2026
Knowledge RetentionWMDP bio (retain)llm chat instruction16May 15, 2026
Machine UnlearningWMDP-bio (forget-set)adversarial safety security16May 15, 2026
Structural ErasureMUSEbio medical16May 15, 2026
Structural ErasureWMDP-cyberbio medical16May 15, 2026
Structural ErasureWMDP chembio medical16May 15, 2026
Structural ErasureWMDP biobio medical16May 15, 2026
Video Moment RetrievalCharadesmultimodalcomputer vision+116May 15, 2026
RSRP PredictionDTU RSRPcomputer vision3d vision geometry16May 15, 2026
Language Understanding and ReasoningGeneral Capability Suite (MMLU, TruthfulQA, HellaSwag, ARC-Easy) (test)nlpllm chat instruction16May 15, 2026
Inference ThroughputGPT-J 6Bmiscellaneous16May 15, 2026
Policy SynthesisGrid-worldrobotics embodied ai16May 15, 2026
Machine UnlearningUnlearning Evaluation Suiteadversarial safety security16May 15, 2026
Machine UnlearningAggregate CIFAR-10, Food, STL, ObjectNet, ImageNetadversarial safety security16May 15, 2026
Closed-loop PlanningBench2Drive Base setrobotics embodied ai16May 15, 2026
Few-shot classificationFC100computer visionnlp+116May 15, 2026
Continual Test-Time AdaptationCIN-C (corr split)computer visiontabular time series16May 15, 2026
Continual Test-Time AdaptationCIN-C iidcomputer visiontabular time series16May 15, 2026
Image ClassificationCCC Hardcomputer vision16May 15, 2026
Image ClassificationCCC Mediumcomputer vision16May 15, 2026
Image ClassificationCCC Easycomputer vision16May 15, 2026