List your company

Research

Benchmarks

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

309,131 benchmarksPage 1288 of 12,366

Benchmarks

TaskDatasetDomainTrendResultsLast update
Image ClassificationImageNet and OOD variantscomputer vision23Jul 7, 2026
Image RestorationCCDD-11computer vision23Jul 7, 2026
Camera Movement UnderstandingACaM synthetic videos (test)computer vision23Jul 7, 2026
Video Multiple Choice Question AnsweringACaM real-world videos 1.0 (test)computer visionmultimodal23Jul 7, 2026
Binary Question AnsweringACaM Synthetic Videos Binary QA (test)nlpllm chat instruction23Jul 7, 2026
Spatial UnderstandingBLINK (val)computer visionmultimodal23Jul 7, 2026
Video Temporal GroundingActivityNet Captions (IID)computer visionnlp23Jul 2, 2026
Object concept unlearningUnlearnCanvascomputer vision23Jul 1, 2026
Needle-in-a-Haystack retrievalNIAH-Single-3 256K contextretrieval search rag23Jun 30, 2026
Needle-in-a-Haystack retrievalNIAH-Single-3 128K contextretrieval search rag23Jun 30, 2026
Needle-in-a-Haystack retrievalNIAH-Single-3 64K contextretrieval search rag23Jun 30, 2026
Needle-in-a-Haystack retrievalNIAH-Single-3 32K contextretrieval search rag23Jun 30, 2026
Needle-in-a-Haystack retrievalNIAH-Single-2 256K contextretrieval search rag23Jun 30, 2026
Needle-in-a-Haystack retrievalNIAH-Single 128K context 2retrieval search rag23Jun 30, 2026
Needle-in-a-Haystack retrievalNIAH-Single-2 32K contextretrieval search rag23Jun 30, 2026
Needle-in-a-Haystack retrievalNIAH-Single-1 256K contextretrieval search rag23Jun 30, 2026
Needle-in-a-Haystack retrievalNIAH-Single-1 128K contextretrieval search rag23Jun 30, 2026
Needle-in-a-Haystack retrievalNIAH-Single-1 64K contextretrieval search rag23Jun 30, 2026
Needle-in-a-Haystack retrievalNIAH-Single-1 32K contextretrieval search rag23Jun 30, 2026
Spatial Causal InferenceSpaCE Air Pollution and Mortality PM2.5 -> m, rd=1, rho_pop confounding 1.0 (test)tabular time series23Jun 30, 2026
Multi-turn Agent TaskALFWorldagents tool use23Jun 29, 2026
ForecastingM1 Competition 1001 (all)tabular time series23Jun 29, 2026
Multiple-choice Video Harmfulness UnderstandingHarmVideoBench (test)computer visionnlp23Jun 26, 2026
Image GenerationWISE-Verifiedimage generation editing23Jun 26, 2026
ClassificationEdible Insect Authentication leave-one-batch-out (LOBO)computer visionnlp+323Jun 26, 2026