Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1852 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Graph Classification | BBBP | 18 | May 22, 2026 | ||
| Speech Recognition | Switchboard CallHome (eval00) | 18 | Apr 14, 2026 | ||
| Novel View Synthesis | DNA Rendering dataset (test) | 18 | Apr 14, 2026 | ||
| Object Detection | Pascal VOC -> Clipart (val) | 18 | Apr 14, 2026 | ||
| Image Clustering | MNIST | 18 | Jul 9, 2026 | ||
| Event-level script generation | V2S 5-minute videos (test) | 18 | Apr 14, 2026 | ||
| Tracking | Bipedal Walking hardware | 18 | Apr 14, 2026 | ||
| 3D Semantic Segmentation | ScanNet | 18 | Jun 23, 2026 | ||
| Multimodal Reward Modeling | MR2Bench Video | 18 | Apr 14, 2026 | ||
| Multimodal Reward Modeling | VideoRewardBench | 18 | Apr 14, 2026 | ||
| Multimodal Reward Modeling | MR2Bench Image | 18 | Apr 14, 2026 | ||
| Robotic task planning and code generation | Advanced | 18 | Apr 14, 2026 | ||
| Robotic task planning and code generation | Basic | 18 | Apr 14, 2026 | ||
| Spoofing Attack Detection | Harm | 18 | Apr 14, 2026 | ||
| Spoofing Attack Detection | Dolly CW | 18 | Apr 14, 2026 | ||
| Question Answering | ConFiQA | 18 | Jun 19, 2026 | ||
| Image Editing | PIE | 18 | Apr 14, 2026 | ||
| Object Detection | Standard Person Detection Dataset | 18 | Apr 14, 2026 | ||
| Corrective Unlearning (Interclass Confusion) | CIFAR100 | 18 | Apr 14, 2026 | ||
| Corrective Unlearning (Interclass Confusion) | CIFAR10 | 18 | Apr 14, 2026 | ||
| Interclass Confusion | CIFAR100 | 18 | Apr 14, 2026 | ||
| Interclass Confusion | CIFAR10 | 18 | Apr 14, 2026 | ||
| Human Pose Estimation | ExLPose LL-H (test) | 18 | Apr 14, 2026 | ||
| Human Pose Estimation | ExLPose WL (test) | 18 | Apr 14, 2026 | ||
| 6D Object Pose Tracking | YCBMultiTrack (synthetic) | 18 | Apr 14, 2026 |