Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1266 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Fine-grained Classification | iNaturalist-19 | 24 | Feb 27, 2026 | ||
| Image Classification | CIFAR-100 pre-trained on CIFAR-10 (test) | 24 | Feb 26, 2026 | ||
| Classification | RSNA | 24 | Feb 26, 2026 | ||
| Semantic Segmentation | COCO-Stuff 10K | 24 | May 21, 2026 | ||
| Robot Manipulation | Real-world Robot Environment 1.0 (test) | 24 | Feb 26, 2026 | ||
| Age Estimation | AgeDB-DIR v1 (test) | 24 | Feb 26, 2026 | ||
| Traffic accident occurrence prediction | Iowa traffic accident dataset (test) | 24 | Feb 26, 2026 | ||
| Fine-grained Image Classification | Oxford Flowers (test) | 24 | Feb 26, 2026 | ||
| Multi-source Domain Generalization | HAC | 24 | Mar 17, 2026 | ||
| Maximum Independent Set | COLLAB (test) | 24 | Jul 2, 2026 | ||
| Minimum Vertex Cover | RB200 (test) | 24 | Feb 26, 2026 | ||
| OOD detection | TinyImageNet (In-distribution) / CIFAR10 (OOD) | 24 | Feb 26, 2026 | ||
| Semantic Segmentation | Synth4D (val) | 24 | Feb 26, 2026 | ||
| Regression | GOOD-ZINC size split, covariate shift | 24 | Feb 26, 2026 | ||
| Classification | Usenet2 | 24 | Feb 26, 2026 | ||
| Classification | Usenet1 | 24 | Feb 26, 2026 | ||
| Classification | Power Supply | 24 | Feb 26, 2026 | ||
| Classification | CLEAR | 24 | Feb 26, 2026 | ||
| Classification | UTKFaces | 24 | Feb 26, 2026 | ||
| Classification | Yearbook | 24 | Feb 26, 2026 | ||
| Temporal Reasoning | TimeQA Hard 1.0 (test) | 24 | Feb 26, 2026 | ||
| Temporal Reasoning | TimeQA Easy 1.0 (test) | 24 | Feb 26, 2026 | ||
| API Invocation Completion | RepoEval 1.0 (test) | 24 | Feb 26, 2026 | ||
| Line Completion | RepoEval 1.0 (test) | 24 | Feb 26, 2026 | ||
| Scene Text Recognition | Union14M L (test) | 24 | Feb 26, 2026 |