Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1330 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Image Classification | Tiny-ImageNet (test) | 23 | Jun 25, 2026 | ||
| Image Classification | iNaturalist IR=500 2018 (test) | 23 | Feb 26, 2026 | ||
| Shadow Detection | ISTD | 23 | Feb 26, 2026 | ||
| Machine Translation | MSCOCO En-De | 23 | Jun 16, 2026 | ||
| Transfer Learning | SentEval Transfer tasks (test) | 23 | Feb 26, 2026 | ||
| Argument Classification | WikiEvents (test) | 23 | Feb 26, 2026 | ||
| Language Modeling | text8 | 23 | Feb 26, 2026 | ||
| Logical Reasoning | ReClor (test-H) | 23 | Feb 26, 2026 | ||
| Logical Reasoning | ReClor (test-e) | 23 | Feb 26, 2026 | ||
| Document Retrieval | NQ 320k (test) | 23 | Feb 26, 2026 | ||
| Co-Salient Object Detection | CoSal 2015 (test) | 23 | Feb 26, 2026 | ||
| Natural Language Inference | HANS | 23 | Feb 27, 2026 | ||
| Few-shot Classification | Oxford Flowers | 23 | Jul 8, 2026 | ||
| 3D Object Detection | DAIR-V2X (val) | 23 | Jul 3, 2026 | ||
| Relation Extraction | FewRel | 23 | May 12, 2026 | ||
| Image Dehazing | RESIDE SOTS 6K (mix) | 23 | Feb 26, 2026 | ||
| Text-to-Video Retrieval | MSRVTT 1K-A (test) | 23 | Feb 26, 2026 | ||
| Image Classification | Flower | 23 | Mar 6, 2026 | ||
| 3D Point Cloud Semantic Segmentation | SemanticSTF SemanticKITTI (val) | 23 | Feb 26, 2026 | ||
| Semantic Segmentation | VOC 2012 | 23 | Feb 26, 2026 | ||
| 6-DoF Object Tracking | YCBInEOAT | 23 | Jul 8, 2026 | ||
| Blind Image Quality Assessment | KonIQ-10k (test) | 23 | Feb 26, 2026 | ||
| Video Frame Interpolation | SNU-FILM (test) | 23 | Feb 26, 2026 | ||
| Clustering | Handwritten (test) | 23 | Feb 26, 2026 | ||
| Video Quality Assessment | LIVE-VQC, KoNViD-1k, YouTube-UGC (Weighted Average) | 23 | Feb 26, 2026 |