Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 250 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Human-Object Interaction Detection | V-COCO | 65 | Feb 26, 2026 | ||
| Instruction Following | AlpacaEval (test) | 65 | May 8, 2026 | ||
| Graph Classification | COX2_MD to COX2 (target) | 65 | Apr 6, 2026 | ||
| Feature Attribution Plausibility | MDACE (test) | 65 | Feb 27, 2026 | ||
| Algebraic Reasoning | AQUA | 65 | Apr 23, 2026 | ||
| Compositional Reasoning | VALSE | 65 | Jun 26, 2026 | ||
| Image Classification | PatternNet | 65 | Jun 23, 2026 | ||
| Long-term forecasting | Traffic | 65 | Mar 11, 2026 | ||
| Long-term forecasting | Weather | 65 | Feb 26, 2026 | ||
| Text-to-Video Retrieval | MSR-VTT 1K (test) | 65 | Apr 14, 2026 | ||
| Molecular property classification | ClinTox (scaffold) | 65 | Mar 19, 2026 | ||
| Semantic Segmentation | ADE20K A-150 (val) | 65 | Feb 26, 2026 | ||
| Classification | GE | 65 | Apr 20, 2026 | ||
| Compositional Zero-Shot Learning | C-GQA open world | 65 | Mar 18, 2026 | ||
| Sentiment Analysis | FPB | 65 | Mar 5, 2026 | ||
| Language Understanding | CMMLU | 65 | Jun 5, 2026 | ||
| Medical Image Segmentation | ACDC | 65 | Mar 16, 2026 | ||
| Backdoor Defense | SST-2 | 65 | Mar 18, 2026 | ||
| Depth Estimation | Cityscapes | 65 | Jun 2, 2026 | ||
| Tumor localization | Camelyon16 (test) | 65 | Mar 18, 2026 | ||
| Image Steganography | Stego260 (test) | 65 | Feb 26, 2026 | ||
| Image Classification | CIFAR100-LT (test) | 65 | May 19, 2026 | ||
| Few-Shot Object Detection | Pascal VOC | 65 | Feb 26, 2026 | ||
| Classification | Digits (test) | 65 | Jun 16, 2026 | ||
| Camouflaged Object Detection | CAMO 250 (test) | 65 | May 26, 2026 |