List your company

Research

Benchmarks

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

309,131 benchmarksPage 1436 of 12,366

Benchmarks

TaskDatasetDomainTrendResultsLast update
Semantic SimilaritySICKnlpretrieval search rag21May 29, 2026
Multimodal Knowledge EditingFGVEditmultimodalllm chat instruction21May 29, 2026
Visual Question AnsweringGQAmultimodalcomputer vision+121Jul 2, 2026
SummarizationCNN/DMnlp21May 29, 2026
Response Harmfulness DetectionResponse Harmfulness Detection Benchmarks (HarmBench, SafeRLHF, BeaverTails, XSTest, WildGuard)adversarial safety security21May 29, 2026
Geometric OptimizationMMDmiscellaneous21May 29, 2026
Geometric OptimizationCPmiscellaneous21May 29, 2026
Open-ended GenerationLLaVA-Benchllm chat instruction21May 29, 2026
RecommendationAL-GR released (test)tabular time series21May 29, 2026
Abstractive SummarizationCNN/DailyMail (test)nlp21Jun 5, 2026
Online Class-Incremental LearningImageNet-100 10 tasks (test)tabular time series21May 29, 2026
Mathematical ReasoningHMMT25llm chat instructionnlp21May 28, 2026
Mathematical ReasoningAIME 25llm chat instructionnlp21May 28, 2026
Mathematical ReasoningAIME 24llm chat instructionnlp21May 28, 2026
Mathematical and Physics ReasoningOLYMPIADBENCHmiscellaneous21May 28, 2026
PlanningNATURALPLANrobotics embodied ai21May 28, 2026
Anomaly LocalizationVisAcomputer vision21May 28, 2026
Anomaly DetectionMVTec-ADtabular time series21May 28, 2026
Super-ResolutionOpenSARShip (test)computer vision21May 28, 2026
Visual Question AnsweringTextVQAmultimodalcomputer vision+121Jul 7, 2026
Image Manipulation LocalizationMagicBrushcomputer vision21Jun 2, 2026
Long-context text understandingLongBench-Prollm chat instructionnlp21May 28, 2026
ForecastingForecasting (test)tabular time series21May 28, 2026
Object-goal navigationHM3D v2robotics embodied aicomputer vision21Jun 4, 2026
Conditional Average Treatment Effect EstimationLinear design N1=500tabular time series21May 28, 2026