Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1317 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Emotion Perception and Recognition | HitEmotion Level 1 | 23 | Feb 26, 2026 | ||
| Emotion Cognition and Reasoning | HitEmotion ECR level 1.0 (test) | 23 | Feb 26, 2026 | ||
| Concept Erasure | P4D | 23 | Mar 13, 2026 | ||
| Consistent Text-to-Image Generation | ConsiStory+ (test) | 23 | Feb 26, 2026 | ||
| Infrared Small Target Detection | NUAA-SIRST | 23 | Apr 1, 2026 | ||
| AIGI Detection | WildRF | 23 | May 22, 2026 | ||
| Visual Grounding | RefCOCO (test) | 23 | May 20, 2026 | ||
| Question Answering | WTQ (test) | 23 | Jul 1, 2026 | ||
| Text-to-Image Generation | GenEval 1024x1024 | 23 | Mar 31, 2026 | ||
| Semantic Segmentation | Karachi | 23 | Feb 26, 2026 | ||
| Semantic Segmentation | Lahore | 23 | Feb 26, 2026 | ||
| Semantic Segmentation | Mumbai | 23 | Feb 26, 2026 | ||
| Semantic Segmentation | Medellin | 23 | Feb 26, 2026 | ||
| Semantic Segmentation | Makoko | 23 | Feb 26, 2026 | ||
| Semantic Segmentation | N. Nairobi | 23 | Feb 26, 2026 | ||
| Semantic Segmentation | El Geneina | 23 | Feb 26, 2026 | ||
| Semantic Segmentation | El Daein | 23 | Feb 26, 2026 | ||
| Few-Shot Segmentation | SUIM | 23 | Jul 1, 2026 | ||
| Open-Vocabulary Segmentation | Pascal VOC 20 2012 (val) | 23 | Feb 26, 2026 | ||
| Instance Segmentation | SIP | 23 | Feb 26, 2026 | ||
| Instance Segmentation | DSIS | 23 | Feb 26, 2026 | ||
| Instance Segmentation | COME15K-H | 23 | Feb 26, 2026 | ||
| Instance Segmentation | COME15K E | 23 | Feb 26, 2026 | ||
| Image Forgery Detection | ForensicHub IFF-Protocol v2025 (test) | 23 | Feb 26, 2026 | ||
| Image Classification | Cross-domain Few-Shot Learning Suite (CUB, Cars, Places, Plantae, EuroSAT, CropDisease) (test) | 23 | Feb 26, 2026 |