List your company

Research

Benchmarks

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

309,131 benchmarksPage 2155 of 12,366

Benchmarks

TaskDatasetDomainTrendResultsLast update
Transfer Performance PredictionAmazon Reviews (test)nlp16May 25, 2026
Transfer Performance PredictionEuroEval (test)nlp16May 25, 2026
Multi-modal UnderstandingMM-Vet v1 (full)multimodal16May 25, 2026
Adversarial RetrievalPython CyberNative C1retrieval search ragadversarial safety security16May 25, 2026
Adversarial RetrievalJava VFD B1retrieval search ragadversarial safety security16May 25, 2026
Adversarial RetrievalPython Alpaca A1retrieval search ragadversarial safety security16May 25, 2026
Survival AnalysisSUPPORTtabular time series16May 25, 2026
Signal ImputationWearable Health Datatabular time series16May 22, 2026
Question AnsweringChronoTQA Tier 1 (147 Phenopackets-grounded onset questions)nlp16May 22, 2026
Text-to-Image GenerationAesthetic-4K v1.0 (test)image generation editing16May 22, 2026
Spreadsheet ManipulationSpreadsheetBenchcode developer ai16May 22, 2026
Image ClassificationBloodMNIST balanced (test)computer vision16May 22, 2026
Federated RecommendationMINDtabular time series16May 22, 2026
Mathematical ReasoningOlympiadllm chat instructionnlp16May 22, 2026
Mathematical ReasoningAIME 24llm chat instructionnlp16May 22, 2026
Mathematical ReasoningAMC 23llm chat instructionnlp16May 22, 2026
Mathematical ReasoningMinervallm chat instructionnlp16May 22, 2026
Mathematical ReasoningMATH 500llm chat instructionnlp16May 22, 2026
Mathematical ReasoningGSM8Kllm chat instructionnlp16May 22, 2026
Scientific Question AnsweringGPQA Mainnlpbio medical16May 22, 2026
Video ReconstructionGOPRO-BR x7 sequence lengthvideo generation editing16May 22, 2026
Video ReconstructionGOPRO-BR x3 sequence lengthvideo generation editing16May 22, 2026
Video ReconstructionrealBR length 9 (test)video generation editing16May 22, 2026
Video ReconstructionrealBR length 5 (test)video generation editing16May 22, 2026
Video ReconstructionrealBR length 3 (test)video generation editing16May 22, 2026