List your company

Research

Benchmarks

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

309,131 benchmarksPage 1999 of 12,366

Benchmarks

TaskDatasetDomainTrendResultsLast update
Traveling Salesman ProblemTSP500 Uniform distribution, scale ≤ 1,000miscellaneous17May 26, 2026
Dynamic Link PredictionUCI-Message (Live-update)graph17May 26, 2026
Fine-grained UnderstandingFG-OVDcomputer visionnlp17May 26, 2026
Node ClassificationEle-Photo (test)graph17May 26, 2026
Subject-driven personalizationDreamBenchimage generation editing17May 26, 2026
CTR PredictionAverage across all four datasets (Criteo, Avazu, KDD12, Industrial)tabular time series17May 26, 2026
Proactive Action PredictionHome Loantabular time series17May 26, 2026
Passage RetrievalAmharic Passage Retrieval Dataset V2 (test)retrieval search rag17May 26, 2026
Web ResearchBrowseCompagents tool useretrieval search rag17May 26, 2026
Long-horizon agent performanceBrowseComp-ZHagents tool usellm chat instruction17May 26, 2026
Textual understandingArena-Hardllm chat instructionnlp17May 26, 2026
Textual understandingAlpacaEval 2llm chat instructionnlp17May 26, 2026
RegressionBindingDBtabular time series17May 26, 2026
ClassificationDrugBankcomputer visionnlp+317May 26, 2026
Anomaly detectionSWaTtabular time series17Jun 2, 2026
Multivariate Time Series Anomaly DetectionPSMtabular time series17May 29, 2026
Question AnsweringNQ PIA (test)nlp17May 25, 2026
Question AnsweringHotpotQA Poison (test)nlp17May 25, 2026
Lesion Grounding and SegmentationAbdomenAtlas 3.0computer visionbio medical17May 22, 2026
Proactive Task-Oriented DialogueFoodDeliverService Courier Regional Bonusllm chat instructionnlp17May 22, 2026
Proactive Task-Oriented DialogueFoodDeliverService Merchant Promotionllm chat instructionnlp17May 22, 2026
Video Anomaly DetectionShanghaiTech Human-Related SHT-HRcomputer vision17May 22, 2026
Video Temporal GroundingCharades TimeLens-Bench (test)computer visionnlp17May 22, 2026
Video Temporal GroundingQVHighlights TimeLens-Bench (test)computer visionnlp17May 22, 2026
Multimodal Embodied ReasoningBEAR 1.0 (test)robotics embodied aimultimodal+117May 22, 2026