List your company

Research

Benchmarks

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

309,131 benchmarksPage 1704 of 12,366

Benchmarks

TaskDatasetDomainTrendResultsLast update
Mathematical ReasoningMath Benchmarks AIME 2024 AIME 2025 OlympiadBenchllm chat instructionnlp19May 13, 2026
Code GenerationCode Benchmarks LCBv6 & MBPP+code developer ai19May 13, 2026
Cross-view Geo-localizationDenseUAV Drone → Satellitecomputer vision19May 15, 2026
Backlit Image EnhancementBacklit300computer vision19May 13, 2026
Helpfulness PredictionAmazon-MRHP Homeretrieval search rag19May 13, 2026
Helpfulness PredictionAmazon-MRHP Electronicsretrieval search rag19May 13, 2026
Helpfulness PredictionAmazon-MRHP Clothingretrieval search rag19May 13, 2026
Helpfulness PredictionLazada-MRHP Homeretrieval search rag19May 13, 2026
Helpfulness PredictionLazada-MRHP Electronicsretrieval search rag19May 13, 2026
Helpfulness PredictionLazada-MRHP Clothingretrieval search rag19May 13, 2026
Forward-direction molecular property editingMolEditRL 500 molecules (test)bio medical19May 12, 2026
Sentence ClassificationCombined dataset (K1, K2, K3, R4)nlp19May 12, 2026
Node ClassificationTexas 1-shotgraph19May 12, 2026
Node ClassificationComputers 1-shotgraph19May 12, 2026
Node ClassificationCornell 1-shotgraph19May 12, 2026
Node ClassificationWisconsin 1-shotgraph19May 12, 2026
Visual GroundingVisual Grounding benchmarks (HRBench8K, VStarBench, RWQA, MMStar, GQA, MMBench v1.1, BLINK)multimodalcomputer vision19May 12, 2026
Forward PDE problem solvingBurgers’miscellaneous19May 12, 2026
Class-Incremental LearningAZ-Class ILcomputer visiontabular time series19May 12, 2026
Class-Incremental LearningEMBER Class-ILcomputer visiontabular time series19May 12, 2026
Satisfiability SolvingLeaking Bucketmiscellaneous19May 12, 2026
Simple P-log Program Computationdicemiscellaneous19May 12, 2026
Video SummarizationTVSum (5FCV)computer visionnlp19May 12, 2026
Science Question AnsweringSQAnlpbio medical19May 12, 2026
Visual Question AnsweringVizWizmultimodalcomputer vision+119May 12, 2026