Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1714 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| OOD Detection | Caltech101 | 19 | Apr 14, 2026 | ||
| Object Erasure | ImageNet-10 Target Concepts SD 1.4 | 19 | Apr 14, 2026 | ||
| Human Reconstruction | NeuMan (test) | 19 | May 25, 2026 | ||
| Medical Image Segmentation | GlaS 2017 (test) | 19 | Apr 13, 2026 | ||
| Stereo Matching | ETH3D (All) | 19 | Jul 1, 2026 | ||
| Face Anti-Spoofing | CSW (CASIA-Surf-CeFA, CASIA-Surf, WMCA) | 19 | Jun 2, 2026 | ||
| Consultation Capability Evaluation | RAPID-IPN | 19 | Apr 13, 2026 | ||
| Consultation Capability Evaluation | ClinicalBench | 19 | Apr 13, 2026 | ||
| Documentation quality evaluation | RAPID-IPN 1.0 (test) | 19 | Apr 13, 2026 | ||
| Documentation quality evaluation | ClinicalBench 1.0 (test) | 19 | Apr 13, 2026 | ||
| Out-of-Distribution Detection | ImageNet-S | 19 | Apr 13, 2026 | ||
| Mathematical reasoning | AMC 2024 | 19 | Apr 14, 2026 | ||
| Sarcasm Detection | SinaSarc (test) | 19 | Apr 10, 2026 | ||
| End-to-End Autonomous Driving | Bench2Drive standard base set (1K clips) | 19 | Apr 10, 2026 | ||
| Video reasoning | MLVU (test) | 19 | May 8, 2026 | ||
| Long-form Video-Language Understanding | LongVideo | 19 | Apr 10, 2026 | ||
| Tabular Classification | HELOC (test) | 19 | Apr 10, 2026 | ||
| Composite score ranking | Butternut Squash function variants discrete domains medium tolerance | 19 | Apr 10, 2026 | ||
| Black-box optimization | Butternut Squash (BS) function variants strict tolerance | 19 | Apr 10, 2026 | ||
| Black-box optimization ranking | BS function 20 variants loose tolerance | 19 | Apr 10, 2026 | ||
| Forecasting | SDWPF | 19 | Apr 20, 2026 | ||
| Human Activity Recognition | HAR Real-world Setting (test) | 19 | May 26, 2026 | ||
| Image-Text Retrieval | CC152K (test) | 19 | Jun 4, 2026 | ||
| Image Classification | CIFAR-10N | 19 | Apr 9, 2026 | ||
| Visual Localization | InLoc (DUC2) | 19 | Jul 7, 2026 |