List your company

Research

Benchmarks

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

309,131 benchmarksPage 2195 of 12,366

Benchmarks

TaskDatasetDomainTrendResultsLast update
Attack Success Rate Evaluation40 diverse smartphone tasks Generate subcategoryadversarial safety security16Apr 9, 2026
Attack Success Rate Evaluation40 diverse smartphone tasks Executeadversarial safety security16Apr 9, 2026
Knowledge EditingMQuAKE-3K (test)nlpllm chat instruction16Apr 8, 2026
Knowledge Base CompletionCWQ 50% KBgraph16Apr 8, 2026
Knowledge Base CompletionCWQ (30% KB)graph16Apr 8, 2026
Knowledge Base CompletionWebQSP 50% KBgraph16Apr 8, 2026
Knowledge Base CompletionWebQSP 30% KBgraph16Apr 8, 2026
Mathematical ReasoningMATH 500llm chat instructionnlp16Apr 8, 2026
Mathematical ReasoningOlympiadBenchllm chat instructionnlp16Apr 8, 2026
Mathematical ReasoningAIME 25llm chat instructionnlp16Apr 8, 2026
Mathematical ReasoningAIME24llm chat instructionnlp16Apr 8, 2026
Closed-loop PlanningBench2Drive base V0.0.3 (train)robotics embodied ai16Jun 16, 2026
Long-video Question AnsweringVideo-MME Long without Subtitlesmultimodalcomputer vision16Apr 8, 2026
Cross-Domain RecommendationBook Movie-Booktabular time series16Apr 8, 2026
Cross-Domain RecommendationMovie-Booktabular time series16Apr 8, 2026
3D ReconstructionETH Herzjesu Small-Scale3d vision geometry16Apr 8, 2026
Text CompletionOpenGen (test)llm chat instruction16Apr 8, 2026
Text CompletionEssays (test)llm chat instruction16Apr 8, 2026
3D Object DetectionOmni3DSUN per-frame (test)3d vision geometrycomputer vision16Apr 8, 2026
3D Object DetectionCA-1M per-frame (test)3d vision geometrycomputer vision16Apr 8, 2026
3D Object DetectionADT per-frame (test)3d vision geometrycomputer vision16Apr 8, 2026
Question AnsweringDynamic Event Benchmark Overallnlp16Apr 8, 2026
Question AnsweringDynamic Event Benchmark Commonsensenlp16Apr 8, 2026
Question AnsweringDynamic Event Benchmark Contemporarynlp16Apr 8, 2026
Question AnsweringDynamic Event Benchmark Historicalnlp16Apr 8, 2026