List your company

Research

Benchmarks

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

309,131 benchmarksPage 1433 of 12,366

Benchmarks

TaskDatasetDomainTrendResultsLast update
Caption Hallucination AnalysisCOCOcomputer visionnlp21Jun 9, 2026
Hierarchical Time Series ForecastingAustralian Tourism (test)tabular time series21Jun 4, 2026
Traveling Salesman Problem (TSP)Synthetic TSP1Kmiscellaneous21Jun 4, 2026
Molecular GenerationHydrocarbon Chainsbio medical21Jun 4, 2026
Molecular GenerationAcrylates (Acry.)bio medical21Jun 4, 2026
CS-MRI reconstructionBrain (test)bio medicalcomputer vision21Jun 4, 2026
Meme GenerationGOAT-G (test)image generation editingnlp21Jun 4, 2026
Meme GenerationMuSE (test)image generation editingnlp21Jun 4, 2026
Meme GenerationMET-Meme (test)image generation editingnlp21Jun 4, 2026
Meme GenerationMemeCap (test)image generation editingnlp21Jun 4, 2026
Meme GenerationMemeReaCon PI-G (test)image generation editingnlp21Jun 4, 2026
Meme GenerationMemeReaCon PC-G (test)image generation editingnlp21Jun 4, 2026
Inpaint (random)FFHQ 256 x 256image generation editing21Jun 30, 2026
Synthetic Tabular Data Generation90 MCAR Scenarios (6 datasets x 5 missing ratios)tabular time series21Jun 4, 2026
Tabular Data GenerationMAR Benchmark 90 Scenarios: 6 datasets × 5 missing ratios (aggregated results)tabular time series21Jun 4, 2026
Causal InferenceJobs (real-world evaluation)tabular time series21Jun 4, 2026
Node Classificationogbn-arxiv 3-shotgraph21Jun 11, 2026
Node ClassificationPubmed 3-shotgraph21Jun 11, 2026
Node ClassificationCiteseer 3-shotgraph21Jun 11, 2026
Molecular Force and Energy PredictionrMD17bio medicaltabular time series21Jun 4, 2026
Molecular Force and Energy PredictionMD17bio medicaltabular time series21Jun 4, 2026
Force PredictionrMD17bio medicaltabular time series21Jun 16, 2026
Hyperspectral ReconstructionNTIRE Hyper-Skin target 2022 (train)computer vision3d vision geometry21Jun 4, 2026
Hyperspectral ReconstructionNTIRE Hyper-Skin target 2020 (train)computer vision3d vision geometry21Jun 4, 2026
Through-plane super-resolutionUK Biobank Flairbio medicalcomputer vision21Jun 4, 2026