List your company

Research

Benchmarks

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

309,131 benchmarksPage 2108 of 12,366

Benchmarks

TaskDatasetDomainTrendResultsLast update
Language UnderstandingIn-domain (test)nlp16Jul 3, 2026
Multitask Language UnderstandingMMLUnlpllm chat instruction16Jul 3, 2026
Mathematical ReasoningOlympiadBenchllm chat instructionnlp16Jul 3, 2026
Foundation Model EvaluationAGIEvalllm chat instructionadversarial safety security16Jul 3, 2026
Multimodal ReasoningMathVistamultimodalnlp16Jul 3, 2026
Multimodal ReasoningMMMUmultimodalnlp16Jul 3, 2026
Visual Object TrackingNfS 30 FPS (test)computer vision16Jul 3, 2026
Node ClassificationTwitch Gamers Balanced Cross-domain setting 12 clients 1:1:1:1:1:1 ratiograph16Jul 2, 2026
Remote Sensing Visual GroundingVRS-Benchcomputer visionnlp16Jul 2, 2026
Text-to-Image GenerationMS-COCO 2014image generation editing16Jul 2, 2026
LoRA Merging PerformanceLoRA problem types Englishllm chat instruction16Jul 2, 2026
General Language CapabilityMMLU, GSM8K, HEval, IFEval, MTBenchllm chat instructionnlp16Jul 2, 2026
Over-refusal EvaluationXSTest, CoCoNotllm chat instructionadversarial safety security16Jul 2, 2026
Visual Question AnsweringAverage over [20-22, 50]multimodalcomputer vision+116Jul 2, 2026
Generalized Category DiscoveryStanford-Cars New classescomputer vision16Jul 2, 2026
Generalized Category DiscoveryStanford-Cars All classescomputer vision16Jul 2, 2026
Generalized Category DiscoveryFGVC-Aircraft New classescomputer vision16Jul 2, 2026
Generalized Category DiscoveryFGVC-Aircraft Old classescomputer vision16Jul 2, 2026
Generalized Category DiscoveryFGVC-Aircraft All classescomputer vision16Jul 2, 2026
Generalized Category DiscoveryCUB-200 New classescomputer vision16Jul 2, 2026
Generalized Category DiscoveryCUB-200 Old classescomputer vision16Jul 2, 2026
Generalized Category DiscoveryCUB-200 All classescomputer vision16Jul 2, 2026
Real World TasksToBmiscellaneous16Jul 2, 2026
Retrievalretrieval benchmark (hold-out)retrieval search rag16Jul 2, 2026
Long-context Question AnsweringLoCoMo (test)llm chat instructionnlp16Jul 2, 2026