List your company

Research

Benchmarks

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

309,131 benchmarksPage 1886 of 12,366

Benchmarks

TaskDatasetDomainTrendResultsLast update
Link PredictionWikiArt-MKG v1graph18Mar 4, 2026
Link PredictionWN9-IMGgraph18Mar 4, 2026
RetrosynthesisUSPTO-50k With Reaction Typebio medical18Mar 4, 2026
Fine-grained DetectionMMFakeBench 10000 (test)computer vision18Mar 4, 2026
Fine-grained DetectionMMFakeBench 1000 (val)computer vision18Mar 4, 2026
Anomaly DetectionBitcoin-OTCtabular time series18May 27, 2026
Tool-Use Agent EvaluationBFCL Multiturn (OOD) v3 (test)agents tool use18Mar 4, 2026
LLM AlignmentUltraFeedback (test)llm chat instructionadversarial safety security18Mar 4, 2026
Speech Quality AssessmentKidsspeech audio18Mar 4, 2026
Speech Quality AssessmentWildspeech audio18Mar 4, 2026
Speech Quality AssessmentNoisyspeech audio18Mar 4, 2026
Speech Quality AssessmentCleanspeech audio18Mar 4, 2026
Safety AlignmentHEx-PHIadversarial safety security18May 20, 2026
Text-to-imageMJHQ 30K (test)image generation editing18Mar 4, 2026
Text-to-imageCOCO 30K (test)image generation editing18Mar 4, 2026
Offline Reinforcement LearningHalfCheetah BodyMass Shift (Medium-Expert)robotics embodied ai18Mar 4, 2026
Offline Reinforcement LearningHalfCheetah BodyMass Shift (Medium-Replay)robotics embodied ai18Mar 4, 2026
Offline Reinforcement LearningHalfCheetah JointNoise Shift (Medium)robotics embodied ai18Mar 4, 2026
Offline Reinforcement LearningHalfCheetah BodyMass Shift (Medium)robotics embodied ai18Mar 4, 2026
Offline Reinforcement LearningHopper Medium-Expert BodyMass Shiftrobotics embodied ai18Mar 4, 2026
Offline Reinforcement LearningHopper Medium-Replay JointNoise Shiftrobotics embodied ai18Mar 4, 2026
Offline Reinforcement LearningWalker2D Medium-Replay BodyMass Shiftrobotics embodied ai18Mar 4, 2026
Offline Reinforcement LearningHalfCheetah Medium-Expert 1T10Srobotics embodied ai18Mar 4, 2026
Offline Reinforcement LearningHopper Medium-Expert 1T10Srobotics embodied ai18Mar 4, 2026
Offline Reinforcement LearningHopper Medium-Replay 1T10Srobotics embodied ai18Mar 4, 2026