List your company

Research

Benchmarks

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

309,131 benchmarksPage 2285 of 12,366

Benchmarks

TaskDatasetDomainTrendResultsLast update
RerankingStackOverflow (test)retrieval search rag16Feb 26, 2026
RerankingSciDocs (test)retrieval search rag16Feb 26, 2026
RerankingMindSmall (test)retrieval search rag16Feb 26, 2026
RerankingAskUbuntu (test)retrieval search rag16Feb 26, 2026
Image ClassificationPet-37 (test)computer vision16Feb 26, 2026
Image ClassificationFlower-102 (test)computer vision16Feb 26, 2026
Image ClassificationCIFAR-10 (test)computer vision16Feb 26, 2026
Multi-concept motion generation (single text)MTT (test)computer visionmultimodal16Feb 26, 2026
Graph-level classificationDDgraph16Feb 26, 2026
Graph-level classificationMalNet Tinygraph16Feb 26, 2026
Property PredictionDOCKSTRINGbio medical16Feb 26, 2026
Graph-level molecular classificationHIVgraphbio medical16Feb 26, 2026
Video-to-Text RetrievalMSR-VTT 1kAmultimodal16Feb 26, 2026
item-salesRELBENCH rel-hm (test)tabular time series16May 18, 2026
driver-positionRELBENCH rel-f1 (test)computer vision16May 18, 2026
user-attendanceRELBENCH rel-event (test)nlp16May 18, 2026
ad-ctrRELBENCH rel-avito (test)tabular time series16May 18, 2026
user-ltvRELBENCH rel-amazon (test)tabular time series16May 18, 2026
Dynamic View SynthesisNeural 3D Video 19 (test)3d vision geometry16Feb 26, 2026
LLM-as-a-judge evaluationVicuna Benchllm chat instruction16Feb 26, 2026
Long-context Language UnderstandingLongBench-e (test)llm chat instructionnlp16Feb 26, 2026
Logical reasoningLogicnlp16Feb 26, 2026
Target behavior attackMBPPadversarial safety security16Feb 26, 2026
Target behavior attackHumanEvaladversarial safety security16Feb 26, 2026
Target behavior attackMMLU phyadversarial safety security16Feb 26, 2026