Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 2102 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| CLS | ColonINST (seen) | 17 | Feb 26, 2026 | ||
| Fine-grained classification | EuroSAT (test) | 17 | Jun 8, 2026 | ||
| Image Classification | ImageNet-S v1 (val) | 17 | Feb 26, 2026 | ||
| Topic Modeling | BBC | 17 | Feb 26, 2026 | ||
| Sparse 3D Reconstruction | ETH Local Feature Benchmark Madrid Metropolis v1.0 | 17 | Feb 26, 2026 | ||
| Abstract graph generation | Community small | 17 | Feb 26, 2026 | ||
| Recommendation | Gowalla (OOD) | 17 | Feb 26, 2026 | ||
| Knowledge Editing | Counterfact (first 2000 edits) | 17 | May 4, 2026 | ||
| Concealed Object Detection | COD10K (2,026) | 17 | Feb 26, 2026 | ||
| Relative Pose Estimation | MegaDepth View | 17 | Feb 26, 2026 | ||
| Commonsense reasoning | HellaSwag 1.0 (test) | 17 | Feb 26, 2026 | ||
| Text Classification | AAPD | 17 | Feb 26, 2026 | ||
| Text Classification | SemEval | 17 | Feb 26, 2026 | ||
| Text Classification | CAVES | 17 | Feb 26, 2026 | ||
| Logical Reasoning | FOLIO-wiki-curated (test) | 17 | Feb 26, 2026 | ||
| First-order logical inference | FOLIO-wiki (testable) | 17 | Feb 26, 2026 | ||
| Model Selection | VOC 2007 | 17 | Feb 26, 2026 | ||
| Model Selection | Flowers | 17 | Feb 26, 2026 | ||
| Model Selection | Food | 17 | Feb 26, 2026 | ||
| Medical Image Segmentation | Lung (CT) (test) | 17 | Feb 26, 2026 | ||
| Video Anomaly Detection | UCF-Crime standard (test) | 17 | Feb 26, 2026 | ||
| Ophthalmic disease diagnosis | Harvard-30k Glaucoma (test) | 17 | Feb 26, 2026 | ||
| Ophthalmic disease diagnosis | Harvard DR 30k (test) | 17 | Feb 26, 2026 | ||
| Ophthalmic disease diagnosis | Harvard-30k AMD (test) | 17 | Feb 26, 2026 | ||
| Novel View Synthesis | LLFF 3-shot | 17 | Feb 26, 2026 |