List your company

Research

Benchmarks

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

309,131 benchmarksPage 1810 of 12,366

Benchmarks

TaskDatasetDomainTrendResultsLast update
Load forecastingLondon Household Electricity (val)tabular time series18Jun 2, 2026
ForecastingComStock (val)tabular time series18Jun 2, 2026
Zero-shot Language UnderstandingLM Evaluation Harness Downstream Suite (HellaSwag, PIQA, WinoGrande, OpenBookQA, SIQA, BoolQ, TriviaQA, MMLU, ARC-Challenge, ARC-Easy, MathQA, SciQ)nlp18Jun 2, 2026
Low-level vision quality assessment (Overall)LL-Bench (test)computer vision18Jun 2, 2026
Underwater Enhancement Quality AssessmentLL-Bench (test)computer vision18Jun 2, 2026
Super Resolution Quality AssessmentLL-Bench (test)computer vision18Jun 2, 2026
Shadow Removal Quality AssessmentLL-Bench (test)computer vision18Jun 2, 2026
Raindrop Removal Quality AssessmentLL-Bench (test)computer vision18Jun 2, 2026
Motion Deblurring Quality AssessmentLL-Bench (test)computer vision18Jun 2, 2026
Low-Light Enhancement Quality AssessmentLL-Bench (test)computer vision18Jun 2, 2026
HDR Enhancement Quality AssessmentLL-Bench (test)computer vision18Jun 2, 2026
Desnowing Quality AssessmentLL-Bench (test)computer vision18Jun 2, 2026
Deraining Quality AssessmentLL-Bench (test)computer vision18Jun 2, 2026
Denoising Quality AssessmentLL-Bench (test)computer vision18Jun 2, 2026
Dehazing Quality AssessmentLL-Bench (test)computer vision18Jun 2, 2026
Defocus Deblurring Quality AssessmentLL-Bench (test)computer vision18Jun 2, 2026
Compression Artifacts Removal Quality AssessmentLL-Bench (test)computer vision18Jun 2, 2026
Question AnsweringHotpotQA (held-out)nlp18Jun 2, 2026
Question Answering2WikiMultiHopQA (held-out)nlp18Jun 2, 2026
Code GenerationCodeEval-Pro BigCodeBench-Lite-Pro and HumanEval-Pro (Held-out)code developer ai18Jun 2, 2026
Code GenerationCodeEval-Pro BigCodeBench-Lite-Pro and HumanEval-Pro (2nd Pass)code developer ai18Jun 2, 2026
Code GenerationCodeEval-Pro BigCodeBench-Lite-Pro and HumanEval-Pro (1st Pass)code developer ai18Jun 2, 2026
Semantic SegmentationARAS400kcomputer vision18Jun 2, 2026
Overall PerformanceMMG2Skill-Bench Averagenlp18Jun 2, 2026
Strategic Decision MakingMMG2Skill-Bench Strategymiscellaneous18Jun 2, 2026