Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1962 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Vessel Segmentation | OCTA 3M FULL projection 500 (test) | 18 | Feb 26, 2026 | ||
| Point Cloud Completion | ShapeNet-55 | 18 | Mar 24, 2026 | ||
| Semantic Segmentation | Cityscapes (val) | 18 | Feb 26, 2026 | ||
| Class Incremental Learning | CIFAR100-B0 5 steps (non-rehearsal) | 18 | Feb 26, 2026 | ||
| Continuous Control | DMC-GB video hard | 18 | Apr 28, 2026 | ||
| Human Pose Estimation | COCO 2014 (val) | 18 | Feb 26, 2026 | ||
| Polyp Segmentation | ClinicDB (test) | 18 | May 19, 2026 | ||
| Summarization | arXiv original (test) | 18 | Feb 26, 2026 | ||
| Generalized Few-Shot Learning | tiered-ImageNet | 18 | Feb 26, 2026 | ||
| Long-context language understanding | SCROLLS (test) | 18 | Feb 26, 2026 | ||
| Facial Expression Recognition | RAF-DB 1.0 (test) | 18 | Feb 26, 2026 | ||
| Named Entity Recognition | CoNLL++ | 18 | Apr 23, 2026 | ||
| Multiple Rotation Averaging | Synthetic dataset (test) | 18 | Feb 26, 2026 | ||
| Video Question Answering | TGIF Transition | 18 | Feb 26, 2026 | ||
| Semantic Segmentation | BDD (test) | 18 | Mar 31, 2026 | ||
| Capacitated Vehicle Routing Problem (CVRP) | CVRP n=150 1K instances (Generalization) | 18 | Feb 26, 2026 | ||
| Flexible Flow Shop Problem | FFSP 20 | 18 | Mar 10, 2026 | ||
| Human-Object Interaction Detection | V-COCO standard (test) | 18 | Feb 26, 2026 | ||
| Text-Video Retrieval | MSRVTT | 18 | Feb 26, 2026 | ||
| Video Action Classification | UCF101 | 18 | Feb 26, 2026 | ||
| Talking head synthesis | User Study | 18 | Feb 26, 2026 | ||
| Image Classification | CIFAR-10 (test) | 18 | Feb 26, 2026 | ||
| Image Classification | CIFAR-100 | 18 | Feb 26, 2026 | ||
| Noisy label detection | Phoneme | 18 | May 6, 2026 | ||
| Noisy label detection | Click | 18 | May 6, 2026 |