List your company

Research

Benchmarks

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

309,131 benchmarksPage 1617 of 12,366

Benchmarks

TaskDatasetDomainTrendResultsLast update
Semantic SegmentationCityscapescomputer vision20Feb 26, 2026
Semantic SegmentationvKITTI 2computer vision20Feb 26, 2026
Rain RemovalRain 0.5computer vision20Feb 26, 2026
Image ClassificationCOVID 4-way 5-shot (test)computer vision20Feb 26, 2026
Image ClassificationCOVID 4-way 1-shot (test)computer vision20Feb 26, 2026
Image ClassificationBrain Tumor MRI 4-way 5-shot (test)computer vision20Feb 26, 2026
Image ClassificationBrain Tumor MRI 1-shot 4-way (test)computer vision20Feb 26, 2026
Image ClassificationXJTU Meningioma 5-shot 4-way (test)computer vision20Feb 26, 2026
Image ClassificationXJTU Meningioma 4-way 1-shot (test)computer vision20Feb 26, 2026
Planning Oriented E2E Autonomous DrivingNAVSIM V2 (Navtest)robotics embodied aicomputer vision20Mar 30, 2026
Node ClassificationPhotograph20Mar 18, 2026
Imbalanced Classification27 imbalanced datasetstabular time series20Feb 26, 2026
Robotic motion control (Run task)Car-Runrobotics embodied ai20Feb 26, 2026
Robotic motion control (Circle task)Car-Circlerobotics embodied ai20Feb 26, 2026
Robotic motion control (Run task)Ball-Runrobotics embodied ai20Feb 26, 2026
Robotic motion control (Circle task)Ball-Circlerobotics embodied ai20Feb 26, 2026
Question Answering2WQA, HPQA, PopQA, and CWQ (test)nlp20Feb 26, 2026
Mathematical ReasoningMATH Minervallm chat instructionnlp20Feb 26, 2026
Mathematical ReasoningAIME 2025llm chat instructionnlp20Feb 26, 2026
Mathematical ReasoningAIME 2024llm chat instructionnlp20Feb 26, 2026
Code GenerationMBPPcode developer ai20Feb 26, 2026
Multi-task Language UnderstandingMMLUnlpllm chat instruction20Feb 26, 2026
CTR predictionAmazon-Review Automotive (test)tabular time series20Feb 26, 2026
CTR predictionAmazon-Review Beauty (test)tabular time series20Feb 26, 2026
CTR predictionAmazon-Review Appliances (test)tabular time series20Feb 26, 2026