Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1343 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Fine-Grained Visual Classification | Caltech Birds-200 | 22 | Jun 25, 2026 | ||
| Instance Segmentation | WHU dataset | 22 | Jun 25, 2026 | ||
| Object Detection | NWPU 2024 (test) | 22 | Jun 25, 2026 | ||
| Object Detection | VHRV 2024 (test) | 22 | Jun 25, 2026 | ||
| 6-DoF UAV Trajectory Estimation | MovingDrone (Ours) | 22 | Jun 25, 2026 | ||
| Training Data Exposure Detection | COCO (train vs Non-training) | 22 | Jun 24, 2026 | ||
| Training Data Exposure Detection | PMC-OA (train) vs ROCO (non-train) | 22 | Jun 24, 2026 | ||
| Concept Unlearning | Nudity | 22 | Jun 24, 2026 | ||
| Fine-grained Clustering | Stanford Cars | 22 | Jun 24, 2026 | ||
| Fine-grained Clustering | Stanford Dogs | 22 | Jun 24, 2026 | ||
| Fine-grained Clustering | CUB Birds | 22 | Jun 24, 2026 | ||
| Anomaly detection | CMS Run 283408 (real collision data) | 22 | Jun 24, 2026 | ||
| Multitask Learning | 8 vision tasks | 22 | Jun 24, 2026 | ||
| Concept Removal | Ring-A-Bell Violence | 22 | Jun 23, 2026 | ||
| Image Editing | RISEBench (test) | 22 | Jun 23, 2026 | ||
| Image Classification | Cars | 22 | Jun 23, 2026 | ||
| Image Classification | Pets | 22 | Jun 23, 2026 | ||
| Image Classification | Caltech101 | 22 | Jun 23, 2026 | ||
| Protein-related instruction tasks | Mol-Instructions | 22 | Jun 23, 2026 | ||
| Single Domain Generalization | OfficeHome | 22 | Jun 23, 2026 | ||
| CodecFake Detection | ECFD - TIS Corpus Elderly E2 (test) | 22 | Jun 23, 2026 | ||
| Instance Segmentation | Industrial-parts dataset (unseen query split) | 22 | Jun 23, 2026 | ||
| Machine Translation | Real-world translation benchmarks Ja→En | 22 | Jun 23, 2026 | ||
| Tense Reinflection | tense reinflection without auxiliary do (hierarchical) | 22 | Jun 23, 2026 | ||
| Link prediction | CiteSeer | 22 | Jun 19, 2026 |