List your company

Research

Benchmarks

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

309,131 benchmarksPage 2175 of 12,366

Benchmarks

TaskDatasetDomainTrendResultsLast update
Unconditional molecule generationGEOM-DRUG (test)bio medical16May 11, 2026
Physical Commonsense ReasoningPIQAnlp16May 29, 2026
Tracking ControlDual-environment payload sweep Aggressive environment, 5x frictionrobotics embodied ai16May 11, 2026
Tracking ControlDual-environment payload sweep Nominal environmentrobotics embodied ai16May 11, 2026
Direction EstimationETH3D3d vision geometrycomputer vision16May 11, 2026
3D Masked Autoencoder Reconstruction3D Medical Domains Mean (val)3d vision geometrybio medical16May 11, 2026
Retrieval-augmented question answeringClashEvalretrieval search ragnlp16May 11, 2026
Stylistic Text GenerationShakespeare style referencesnlp16May 8, 2026
Safety EvaluationWildGuardadversarial safety security16May 8, 2026
Image CompressionImageNet-1k 224 × 224computer vision16May 8, 2026
Image CompressionKodak 512 × 768 and 768 × 512computer vision16May 8, 2026
Compositional Video GenerationDCR-Bench (full evaluation set)video generation editing16May 8, 2026
Zero-shot EvaluationMean tasks zero-shot (test)nlpllm chat instruction16May 8, 2026
Quantile RegressionScenario 3 n=10000tabular time series16May 8, 2026
Quantile RegressionScenario 3 n=5000tabular time series16May 8, 2026
Quantile RegressionScenario 3 n=1000tabular time series16May 8, 2026
Quantile RegressionScenario 2 n=10000tabular time series16May 8, 2026
Quantile RegressionScenario 2 (n=5000)tabular time series16May 8, 2026
Quantile RegressionScenario 2 n=1000tabular time series16May 8, 2026
Quantile RegressionScenario 1 n=10000tabular time series16May 8, 2026
Quantile RegressionScenario 1 (n=5000)tabular time series16May 8, 2026
Quantile RegressionScenario 1 n=1000tabular time series16May 8, 2026
Disease PredictionSRPBSbio medicaltabular time series16May 8, 2026
Disease Prediction (ASD)ABIDE CC200bio medicaltabular time series16May 8, 2026
Disease Prediction (ASD)ABIDEbio medicaltabular time series16May 8, 2026