Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1139 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Image Classification | CIFAR10 original and noisy labels (test) | 25 | Feb 26, 2026 | ||
| Phonetic Transcription | Libri-Dys (test) | 25 | Feb 26, 2026 | ||
| Phonetic Transcription | VCTK++ (test) | 25 | Feb 26, 2026 | ||
| Video Depth Estimation | KITTI (test) | 25 | Apr 10, 2026 | ||
| Aspect Sentiment Triplet Extraction | D2 (16Res) | 25 | Feb 26, 2026 | ||
| Aspect Sentiment Triplet Extraction | D2 15Res | 25 | Feb 26, 2026 | ||
| Aspect Sentiment Triplet Extraction | D2 14Lap | 25 | Feb 26, 2026 | ||
| Aspect Sentiment Triplet Extraction | D2 14Res | 25 | Feb 26, 2026 | ||
| Multimodal In-Context Learning | VL-ICL benchmark | 25 | Feb 26, 2026 | ||
| Semantic Segmentation | Cityscapes target domain | 25 | Feb 26, 2026 | ||
| Regression | Naval | 25 | Jul 9, 2026 | ||
| Synthetic Speech Detection | ASVspoof DF 2021 (eval) | 25 | Mar 31, 2026 | ||
| Gaussian deblur | FFHQ 256x256 | 25 | Mar 4, 2026 | ||
| Trajectory Prediction | nuScenes (Leaderboard) | 25 | Jun 29, 2026 | ||
| Camera Pose Estimation | Tanks and Temples | 25 | May 7, 2026 | ||
| Saliency Prediction | SALICON (test) | 25 | Feb 26, 2026 | ||
| Whole-Body Human Mesh Recovery | EgoBody EgoSet (test) | 25 | Mar 31, 2026 | ||
| Temporal Question Answering | TimeQA Hard | 25 | Jun 16, 2026 | ||
| Classification | BCI IV-2a | 25 | Mar 10, 2026 | ||
| Image Deblurring | CelebA (test) | 25 | May 12, 2026 | ||
| Safety Evaluation | SafetyBench en | 25 | Feb 26, 2026 | ||
| Image Classification | SIIM-ACR | 25 | May 26, 2026 | ||
| General Performance | AlpacaEval | 25 | Feb 26, 2026 | ||
| Language Modeling | WikiText (held-out) | 25 | Feb 26, 2026 | ||
| Question Answering | CQA | 25 | Feb 26, 2026 |