Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1652 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Intent Classification | HWU64 10-shot | 20 | Feb 26, 2026 | ||
| Intent Classification | BANKING77 10-shot | 20 | Feb 26, 2026 | ||
| Semantic Segmentation | BDD target domain | 20 | Feb 26, 2026 | ||
| Semantic Segmentation | Mapillary target domain | 20 | Feb 26, 2026 | ||
| Interactive Text Editing (Insertion) | CoAuthor (test) | 20 | Feb 26, 2026 | ||
| Interactive Text Editing (Continuation) | CoAuthor (test) | 20 | Feb 26, 2026 | ||
| Causal Inference | IHDP | 20 | Feb 26, 2026 | ||
| Image Classification | ImageNet V2 A Sketch ObjNet R | 20 | Feb 26, 2026 | ||
| Text Classification | EmojiEval (test) | 20 | Feb 26, 2026 | ||
| Object Detection | Malaria 12 (test) | 20 | Feb 26, 2026 | ||
| Cell Detection | Raabin-WBC HCM to LCM domain adaptation (test) | 20 | Feb 26, 2026 | ||
| Language Modeling | Pre-training corpus (train) | 20 | Feb 26, 2026 | ||
| Screenshot-to-code | Design2Code | 20 | Feb 26, 2026 | ||
| Image Classification | CIFAR-10 Instance-Dependent Noise 40% (test) | 20 | Mar 19, 2026 | ||
| Image Classification | CIFAR-10 Instance-Dependent Noise 20% (test) | 20 | Mar 19, 2026 | ||
| OC/OD Segmentation | RIGA+ Average (BASE1-3) | 20 | Feb 26, 2026 | ||
| OC/OD Segmentation | RIGA+ BASE3 | 20 | Feb 26, 2026 | ||
| OC/OD Segmentation | RIGA+ BASE2 | 20 | Feb 26, 2026 | ||
| OC/OD Segmentation | RIGA+ BASE1 | 20 | Feb 26, 2026 | ||
| Dialogue Generation | ConvAI2 (test) | 20 | Apr 15, 2026 | ||
| Prostate Segmentation | ProstateX | 20 | Feb 26, 2026 | ||
| Whole-body pose estimation | COCO-WholeBody 1.0 | 20 | Feb 26, 2026 | ||
| Out-of-Distribution Reasoning | OOD Reasoning Datasets (MMLU-S, GPQA, ARC, BBH) (test) | 20 | Feb 26, 2026 | ||
| Image Denoising | Set12 resized (test) | 20 | Feb 26, 2026 | ||
| Prostate Segmentation | HK (test) | 20 | Feb 26, 2026 |