List your company

Research

Benchmarks

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

309,131 benchmarksPage 1705 of 12,366

Benchmarks

TaskDatasetDomainTrendResultsLast update
Visual Question AnsweringGQAmultimodalcomputer vision+119May 12, 2026
Diagram UnderstandingAI2Dcomputer visionnlp19May 12, 2026
Multimodal ReasoningMMBenchmultimodalnlp19May 12, 2026
Multimodal EvaluationMMEmultimodal19May 12, 2026
Property OptimizationPMV21 JNK3 (test)bio medicaltabular time series19May 12, 2026
Iterative Self-OptimizationOPT-BENCH-ML 20 steps 1.0llm chat instructionagents tool use19May 12, 2026
Iterative Self-OptimizationOPT-BENCH ML environments 10 steps 1.0llm chat instructionagents tool use19May 12, 2026
Iterative Self-OptimizationOPT-BENCH 5 steps 1.0 (ML environments)llm chat instructionagents tool use19May 12, 2026
ClusteringIsolettabular time series19May 12, 2026
Image EditingGEdit-Benchimage generation editing19May 12, 2026
Offline Reinforcement LearningD4RL Gym-MuJoCo walker2d-expertrobotics embodied ai19Jun 15, 2026
Image-to-Text RetrievalCOCO 2017multimodalretrieval search rag19May 12, 2026
Class Incremental LearningImageNet-R B100 Inc20 (test)computer visiontabular time series19May 14, 2026
Optimal LiquidationOffline Optimal Liquidation Environmenttabular time series19Jun 2, 2026
Multimodal SearchBCVLretrieval search ragmultimodal19May 11, 2026
Multimodal SearchLiveVQAretrieval search ragmultimodal19May 11, 2026
Multimodal SearchMMSearchretrieval search ragmultimodal19May 11, 2026
Conditional GenerationMNISTimage generation editing19Jul 8, 2026
Claim VerificationPrimeFacts Five Classnlp19May 8, 2026
Claim VerificationPrimeFacts Two Classnlp19May 8, 2026
Human Motion SegmentationMADcomputer vision19May 8, 2026
Agentic SearchBrowseCompagents tool useretrieval search rag19Jun 18, 2026
Image ClassificationSpawrious M2M-Mediumcomputer vision19May 7, 2026
Image ClassificationSpawrious M2M-Easycomputer vision19May 7, 2026
Image ClassificationSpawrious O2O-Mediumcomputer vision19May 7, 2026