List your company

Research

Benchmarks

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

309,131 benchmarksPage 1899 of 12,366

Benchmarks

TaskDatasetDomainTrendResultsLast update
Semantic SegmentationPangaea Extended (50% train)computer vision18Feb 26, 2026
Single-Image Super-resolutionSR-CACO-2 full image (test)computer vision18Feb 26, 2026
Medical Image RestorationACDCbio medicalcomputer vision18Jul 2, 2026
Face Image Quality AssessmentSFIQA-Bench (test)computer vision18Feb 26, 2026
Facial Image Quality AssessmentGFIQA-20Kcomputer vision18Feb 26, 2026
Spoken Term DetectionTIMIT OOVspeech audio18Jun 26, 2026
Spoken Term DetectionTIMIT (IV)speech audio18Jun 26, 2026
Audio QA Correctness AssessmentMMAU and MMAR unseen question-based (test)speech audionlp18Feb 26, 2026
Authentication RestorationSafeSpeech Protected TTS Speech (test)speech audio18Feb 26, 2026
Authentication RestorationPOP Protected TTS Speech (test)speech audio18Feb 26, 2026
Authentication RestorationGAN-ADV Protected TTS Speech (test)speech audio18Feb 26, 2026
Authentication RestorationAttack-VC Protected TTS Speech (test)speech audio18Feb 26, 2026
Authentication RestorationAntiFake Protected TTS Speech (test)speech audio18Feb 26, 2026
Audio ClassificationESC50speech audio18Jul 1, 2026
Audio ClassificationAverage over 11 datasetsspeech audio18Jul 1, 2026
Linear correlation between human MOS and automatic metricsLibriTTS-P (test)speech audio18Feb 26, 2026
Linear correlation between human MOS and automatic metricsTextrolSpeech (test)speech audio18Feb 26, 2026
Audio GenerationSpeech clean (test)speech audio18Feb 26, 2026
Audio GenerationSpeech Noise SNR=-10 (test)speech audio18Feb 26, 2026
Audio GenerationSound Clean (test)speech audio18Feb 26, 2026
Audio GenerationSound Noise SNR=-10 (test)speech audio18Feb 26, 2026
Audio GenerationMusic clean (test)speech audio18Feb 26, 2026
Audio GenerationMusic Noise SNR=-10 (test)speech audio18Feb 26, 2026
Automatic Speech RecognitionCommonVoice (test)speech audio18Jun 2, 2026
Audio Quality AssessmentLibriSpeechspeech audio18Feb 26, 2026