Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1268 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Image Classification | Pascal VOC low-shot 2007 | 24 | Feb 26, 2026 | ||
| Multimodal Recommendation | Clothing (test) | 24 | Mar 4, 2026 | ||
| Multimodal Recommendation | Sports (test) | 24 | Mar 4, 2026 | ||
| HOI Detection | HICO-DET v1 (test) | 24 | Feb 26, 2026 | ||
| Multi-label classification | Open Images | 24 | Feb 27, 2026 | ||
| Multi-task Language Understanding | LM Evaluation Harness (test) | 24 | Feb 26, 2026 | ||
| Image Classification | ImageNet Subset | 24 | Mar 5, 2026 | ||
| Toxicity Generation | ToxiGen | 24 | Feb 26, 2026 | ||
| Truthfulness and Informativeness | TruthfulQA | 24 | Feb 26, 2026 | ||
| Semantic Segmentation | COCO-20i Fold-3 | 24 | Feb 26, 2026 | ||
| Semantic Segmentation | COCO-20i Fold-2 | 24 | Feb 26, 2026 | ||
| Semantic Segmentation | COCO 20i Fold-1 | 24 | Feb 26, 2026 | ||
| Semantic Segmentation | COCO-20i Fold-0 | 24 | Feb 26, 2026 | ||
| Knowledge Graph Question Answering | MetaQA 2-hop (test) | 24 | Mar 4, 2026 | ||
| Survival Prediction | TCGA-READ | 24 | Feb 26, 2026 | ||
| Diabetic Retinopathy grading | FGADR ESDG (test) | 24 | Feb 26, 2026 | ||
| Diabetic Retinopathy grading | APTOS ESDG (test) | 24 | Feb 26, 2026 | ||
| Point Cloud Reconstruction | ModelNet40 (test) | 24 | Mar 24, 2026 | ||
| Phase Classification | IKEA ASM | 24 | Feb 26, 2026 | ||
| Phase Classification | Pouring | 24 | Feb 26, 2026 | ||
| Image Captioning | COCO 2017 (val) | 24 | Feb 26, 2026 | ||
| Entity Alignment | FB15K-YAGO15K (50% train) | 24 | Feb 26, 2026 | ||
| Entity Alignment | FB15K-DB15K 50% (train) | 24 | Feb 26, 2026 | ||
| Medical Image Registration | IXI (test) | 24 | Feb 26, 2026 | ||
| Conversational Search | CAsT 20 | 24 | Apr 10, 2026 |