Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1958 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Sentiment and topic classification | Subj | 18 | Mar 5, 2026 | ||
| Push and Switch | OpenAI Fetch - Push and Switch 3-Push + 3-Switch (S+O) (test) | 18 | Feb 26, 2026 | ||
| Zero-shot Classification | ModelNet40 | 18 | May 19, 2026 | ||
| Node Classification | genius 50/25/25 (test) | 18 | Feb 26, 2026 | ||
| Fine-grained Image Classification | Stanford Dogs | 18 | Feb 26, 2026 | ||
| Ejection Fraction Estimation | EchoNet-Dynamic (test) | 18 | Jun 23, 2026 | ||
| Semantic Segmentation | UDS merged (test) | 18 | Feb 26, 2026 | ||
| Semantic Segmentation | MSeg (test) | 18 | Feb 26, 2026 | ||
| Node Classification | ogbn-products | 18 | Jun 24, 2026 | ||
| Node Classification | 18 | Jun 24, 2026 | |||
| Medical Image Segmentation | MRI | 18 | Feb 26, 2026 | ||
| Medical Image Segmentation | OCT | 18 | Feb 26, 2026 | ||
| Medical Image Segmentation | Cataract Surgery | 18 | Feb 26, 2026 | ||
| Entity Alignment | FB15K-DB15K (20% train) | 18 | Feb 26, 2026 | ||
| Polyp Segmentation | CVC source Kvasir target domain | 18 | Feb 26, 2026 | ||
| Polyp Segmentation | Kvasir source: CVC target domain | 18 | Feb 26, 2026 | ||
| Occupation Classification | Bias-in-Bios | 18 | Feb 26, 2026 | ||
| Adversarial Detection | AG News | 18 | Feb 26, 2026 | ||
| Texture Reconstruction | HO-3D YCB Objects | 18 | Feb 26, 2026 | ||
| Stereo Matching | IMC Phototourism 2021 (test) | 18 | Feb 26, 2026 | ||
| Novel View Synthesis | ScanNet unseen real scenes | 18 | Mar 19, 2026 | ||
| Node classification | PascalVOC-SP (test) | 18 | May 14, 2026 | ||
| Machine Translation | WMT'16 En-Ro (test) | 18 | Feb 27, 2026 | ||
| Natural Language Processing | T0 benchmark | 18 | Feb 26, 2026 | ||
| Medical Image Segmentation | NCI (test) | 18 | Feb 26, 2026 |