Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1382 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Quantization Performance Summary | Aggregated Benchmarks HellaSwag, MMLU, Arc-C, MATH-500 | 22 | Feb 27, 2026 | ||
| Mathematical Reasoning | Math500 | 22 | Feb 26, 2026 | ||
| Multimodal deep search and reasoning | BrowseComp V3 | 22 | Feb 26, 2026 | ||
| Object Goal Navigation | HM3D V2 (val) | 22 | Mar 24, 2026 | ||
| Precipitation Nowcasting | CIKM | 22 | Jun 4, 2026 | ||
| 3D Object Detection (Pedestrian) | KITTI (test) | 22 | Feb 27, 2026 | ||
| Image Reconstruction | Waymo | 22 | Apr 7, 2026 | ||
| Image Classification | ImageNet 1k (val) | 22 | Feb 26, 2026 | ||
| Medical order extraction | SIMORD (test) | 22 | Feb 26, 2026 | ||
| Semantic Segmentation | PASTIS (test) | 22 | May 21, 2026 | ||
| Fetal Head Segmentation | ES-TCB | 22 | Feb 26, 2026 | ||
| No-Reference Image Quality Assessment | Average across all datasets | 22 | Jun 30, 2026 | ||
| Point Cloud Quality Assessment | SJTU WPC (cross-dataset) | 22 | Feb 26, 2026 | ||
| Keyword Spotting | GSC | 22 | Feb 26, 2026 | ||
| Automatic Speech Recognition | Libri-Adapt Exp. 2 | 22 | Feb 26, 2026 | ||
| Automatic Speech Recognition | TED-Lium 20 (test) | 22 | Feb 26, 2026 | ||
| Automatic Speech Recognition | SPGISpeech 19 (test) | 22 | Feb 26, 2026 | ||
| Automatic Speech Recognition | LibriSpeech clean 18 | 22 | Feb 26, 2026 | ||
| Audio Classification | SESA | 22 | Jun 18, 2026 | ||
| Child's Automatic Speech Recognition | RSR | 22 | Feb 26, 2026 | ||
| Audio Spoof Detection | PartialSpoof (PS) (test) | 22 | Feb 26, 2026 | ||
| Motion Planning | nuScenes | 22 | Jul 7, 2026 | ||
| Sensor Data Provisioning | EDGAR and vEDGAR HiL | 22 | Feb 26, 2026 | ||
| Instance-Image-Goal Navigation | HM3D | 22 | May 20, 2026 | ||
| Trajectory Optimization and Tracking | 1/10-scale racing simulation platform Numerical Simulation 1.0 | 22 | Feb 26, 2026 |