Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1150 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Automatic Speech Recognition | LibriSpeech 100h clean (dev) | 25 | Jun 11, 2026 | ||
| Dependency Parsing | WSJ 10 or fewer words (test) | 25 | Feb 26, 2026 | ||
| RGB saliency detection | ECSSD | 25 | Jul 8, 2026 | ||
| Vehicle Trajectory Prediction | HighD (test) | 25 | Apr 20, 2026 | ||
| Few-shot Image Classification | ChestX CDFSL (test) | 25 | Feb 26, 2026 | ||
| Language Modeling | WikiText-103 word-level (val) | 25 | Jun 24, 2026 | ||
| Slot Filling | SNIPS (test) | 25 | Feb 26, 2026 | ||
| Abstractive Summarization | CNN/DailyMail | 25 | Feb 26, 2026 | ||
| Speech Recognition | LRS3-TED | 25 | Feb 26, 2026 | ||
| Semantic Segmentation | PASCAL-5i (test) | 25 | Feb 26, 2026 | ||
| Face Alignment | WFLW Blur Subset | 25 | Feb 26, 2026 | ||
| Face Alignment | WFLW Expression | 25 | Feb 26, 2026 | ||
| Image Harmonization | S-Adobe5K (test) | 25 | Feb 26, 2026 | ||
| Image Classification | ImageNet 1k (val) | 25 | Feb 26, 2026 | ||
| Image Retrieval | VehicleID Medium | 25 | Feb 26, 2026 | ||
| Image Denoising | BSD68 Noise Level 25 | 25 | Feb 26, 2026 | ||
| Response Selection | ConvAI2 (dev) | 25 | Feb 26, 2026 | ||
| Monocular Depth Estimation | KITTI Improved annotated depth maps Eigen (test) | 25 | Feb 26, 2026 | ||
| Action Segmentation | GTEA (test) | 25 | Feb 26, 2026 | ||
| Pedestrian Trajectory Prediction | HOTEL ETH (test) | 25 | Feb 26, 2026 | ||
| Visual Question Answering | PlotQA | 25 | Feb 26, 2026 | ||
| Zero-shot Video Object Segmentation | DAVIS 2016 (val) | 25 | Feb 26, 2026 | ||
| Image Classification | tiered-ImageNet | 25 | Feb 26, 2026 | ||
| Video Object Segmentation | FBMS | 25 | May 29, 2026 | ||
| Nuclear Instance Segmentation | TNBC | 25 | May 29, 2026 |