List your company

Research

Benchmarks

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

309,131 benchmarksPage 1804 of 12,366

Benchmarks

TaskDatasetDomainTrendResultsLast update
Multimodal ReasoningMultimodal Reasoning Benchmarks Combinedmultimodalnlp18Jun 8, 2026
General Multimodal ReasoningGeneral Multimodal Reasoning Suite MMK12, Geo3K, MathVerse, MathVista, We-Mathmultimodal18Jun 8, 2026
Voice CloningSeed-TTS-Eval ZH-Hard (test)speech audio18Jun 8, 2026
Keypoint EstimationKP-SAR-Aircraft 1.0 (test)computer vision18Jun 8, 2026
Text-to-Image GenerationImageNetimage generation editing18Jun 8, 2026
Ramp Flow PredictionXueBu 10mintabular time series18Jun 8, 2026
Ramp Flow PredictionXueBu 5mintabular time series18Jun 8, 2026
Ramp Flow PredictionXueBu 3mintabular time series18Jun 8, 2026
Ramp Flow PredictionDanYangXinQu 10mintabular time series18Jun 8, 2026
Ramp Flow PredictionDanYangXinQu 5mintabular time series18Jun 8, 2026
Ramp Flow PredictionDanYangXinQu 3mintabular time series18Jun 8, 2026
Censored-engressionSynthetic dataset Regime (D)adversarial safety security18Jun 5, 2026
Multivariate Survival AnalysisSynthetic multivariate survival Conditional uniform censoringtabular time series18Jun 5, 2026
Multivariate Survival AnalysisSynthetic multivariate survival Uniform censoringtabular time series18Jun 5, 2026
Multivariate Survival AnalysisSynthetic multivariate survival Administrative censoringtabular time series18Jun 5, 2026
Machine UnlearningRWKU canonical ten-subject batchadversarial safety security18Jun 5, 2026
Cross-domain recommendationCross-Livetabular time series18Jun 5, 2026
Cross-domain recommendationCross-Adtabular time series18Jun 5, 2026
Cross-domain recommendationCross-Producttabular time series18Jun 5, 2026
Cross-domain recommendationCross-Videotabular time series18Jun 5, 2026
SummarizationXSumnlp18Jun 11, 2026
Reasoning / RewardRRllm chat instruction18Jun 5, 2026
Human Safety / AlignmentHSadversarial safety security18Jun 5, 2026
Agent Action PerformanceASRagents tool use18Jun 5, 2026
Code GenerationCodecode developer ai18Jun 5, 2026