Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1204 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Vascular Image Segmentation | FVS-HRF | 24 | Apr 14, 2026 | ||
| Vascular Image Segmentation | FVS-DRIVE | 24 | Apr 14, 2026 | ||
| Mathematical Reasoning | AMC 2023 | 24 | May 12, 2026 | ||
| Visual Perception | HallusionBench | 24 | Jun 4, 2026 | ||
| Question Answering | Average (TVQA, SciQ, NQ-Open) (test) | 24 | Apr 14, 2026 | ||
| Question Answering | SciQ In-Domain (test) | 24 | Apr 14, 2026 | ||
| Visual Place Recognition | hk_flood | 24 | Apr 14, 2026 | ||
| Visual Place Recognition | sf_flood | 24 | Apr 14, 2026 | ||
| Image Classification | Office-Home v1 (target set) | 24 | Apr 14, 2026 | ||
| Virtual Staining | HEMIT 13 (full dataset) | 24 | Apr 14, 2026 | ||
| Dec-POMDP Planning | MARS ROVERS | 24 | Apr 13, 2026 | ||
| Dec-POMDP Planning | DEC TIGER | 24 | Apr 13, 2026 | ||
| Machine Unlearning | CIFAR-10 30% random data forgetting | 24 | Apr 14, 2026 | ||
| Video Question Answering | LONGVIDEOBENCH Medium | 24 | Apr 13, 2026 | ||
| UAV Image Restoration | MDUR Zero-Shot Settings | 24 | Apr 13, 2026 | ||
| UAV Image Restoration | MDUR Seen Settings | 24 | Apr 13, 2026 | ||
| Multi-view Classification | PIE | 24 | May 26, 2026 | ||
| Image Manipulation Localization | IMD20 | 24 | Apr 13, 2026 | ||
| Linguistic Steganography | LLM Steganography Evaluation Dataset | 24 | Apr 13, 2026 | ||
| Partial Multi-Label Learning | image | 24 | Apr 13, 2026 | ||
| Multimodal Reasoning Average | Combined (M3-Bench + Video-MME-Long) | 24 | Apr 13, 2026 | ||
| Long-form Video Multimodal Evaluation | Video-MME Long | 24 | Apr 13, 2026 | ||
| Multimodal Reasoning | M3-Bench web | 24 | Apr 13, 2026 | ||
| Multimodal Reasoning | M3-Bench robot | 24 | Apr 13, 2026 | ||
| Table Question Answering | SSTQA (test) | 24 | Apr 13, 2026 |