List your company

Research

Benchmarks

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

309,131 benchmarksPage 2144 of 12,366

Benchmarks

TaskDatasetDomainTrendResultsLast update
Melanoma classificationMIDcbio medicalcomputer vision16Jun 1, 2026
Melanoma classificationMcbio medicalcomputer vision16Jun 1, 2026
ForecastingExchange Ratetabular time series16Jun 1, 2026
Gene-gene relationship recallCombined Gene-Gene Relationships (CORUM, hu.MAP, Signor, Reactome-PPI, StringDB) (Whole-genome)bio medicalnlp16Jun 1, 2026
LTL Property VerificationGrid-world environmentmiscellaneous16Jun 1, 2026
general reasoningGPQAllm chat instructionnlp16Jun 1, 2026
math reasoningThmQAllm chat instructionnlp16Jun 1, 2026
math reasoningMATH 500llm chat instructionnlp16Jun 1, 2026
Discretized Goal NavigationReplicarobotics embodied ai16Jun 1, 2026
Semantic Instance TargetingReplicarobotics embodied aicomputer vision16Jun 1, 2026
Next-character predictionMultilingual NLInlp16Jun 1, 2026
Gender RecognitionCelebAMask-HQcomputer vision16Jun 1, 2026
Identity ClassificationCelebAMask-HQcomputer vision16Jun 1, 2026
Lesion SegmentationMSWAL (five-fold cross-val)bio medicalcomputer vision16Jun 1, 2026
Audio-Visual Deepfake DetectionFakeAVCeleb (test)multimodalspeech audio+116Jun 1, 2026
Multi-hop Question AnsweringMulti-hop QA Datasets calculated average (test)nlpretrieval search rag16Jun 1, 2026
Multi-hop Question AnsweringTriviaQA fixed split (test)nlpretrieval search rag16Jun 1, 2026
Multi-hop Question AnsweringPopQA fixed split (test)nlpretrieval search rag16Jun 1, 2026
Multi-hop Question AnsweringNatural Questions (NQ) fixed split (test)nlpretrieval search rag16Jun 1, 2026
Multi-hop Question AnsweringMusique fixed split (test)nlpretrieval search rag16Jun 1, 2026
Multi-hop Question AnsweringHotpotQA fixed (test)nlpretrieval search rag16Jun 1, 2026
Binary ClassificationLGGtabular time series16Jun 1, 2026
Binary ClassificationROSMAPtabular time series16Jun 1, 2026
Multi-class classificationKIPANtabular time series16Jun 1, 2026
LLM-judge evaluation on humanities rubricshared human-rated question set n=100 (test)llm chat instructionnlp16Jun 1, 2026