Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1185 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Vector Quantization | BigANN1M D = 128 (test) | 24 | May 15, 2026 | ||
| Vector Quantization | Deep1M D = 96 (test) | 24 | May 15, 2026 | ||
| Pixel-level forgery localization | CASIAv1, COVERAGE, Columbia, NIST16, CocoGlide, AutoSplice nature-oriented (full) | 24 | May 15, 2026 | ||
| Image-level Document Forgery Detection | DocTamper FCD | 24 | May 15, 2026 | ||
| Spatiotemporal traffic forecasting | Milan-SMS | 24 | May 15, 2026 | ||
| Spatiotemporal traffic forecasting | Trentino-SMS | 24 | May 15, 2026 | ||
| Spatiotemporal traffic forecasting | Trentino-Internet | 24 | May 15, 2026 | ||
| 3D Object Detection | Pi3DET Quadruped platform | 24 | May 14, 2026 | ||
| 3D Object Detection | Pi3DET Drone platform (test) | 24 | May 14, 2026 | ||
| Uncertainty Quantification | MMLU-pro (test) | 24 | Jun 1, 2026 | ||
| logical reasoning | DetectiveQA | 24 | May 14, 2026 | ||
| geometry proof generation | geometry | 24 | May 14, 2026 | ||
| number theory problem solving | number theory | 24 | May 14, 2026 | ||
| Novel View Synthesis | DL3DV 256×448 (test) | 24 | May 14, 2026 | ||
| Novel View Synthesis | RealEstate10K 360×640 (test) | 24 | May 14, 2026 | ||
| Image Classification | ISIC (test) | 24 | May 19, 2026 | ||
| Multi-agent coordination | TrafficJunction-Large (TJ-L) ablation (test) | 24 | May 14, 2026 | ||
| Multi-agent coordination | TrafficJunction Small ablation (test) | 24 | May 14, 2026 | ||
| Multi-agent coordination | PredatorPrey-Diagonal (PP-D) ablation (test) | 24 | May 14, 2026 | ||
| Multi-agent coordination | PredatorPrey-Orthogonal (PP-O) (ablation test) | 24 | May 14, 2026 | ||
| Multi-agent coordination | Navigation ablation Clean (test) | 24 | May 14, 2026 | ||
| PredatorPrey | PredatorPrey Diagonal | 24 | May 14, 2026 | ||
| PredatorPrey | PredatorPrey Orthogonal (PP-O) | 24 | May 14, 2026 | ||
| Multi-agent Reinforcement Learning | TrafficJunction Large (TJ-L) | 24 | May 14, 2026 | ||
| Multi-agent Reinforcement Learning | TrafficJunction Small (TJ-S) | 24 | May 14, 2026 |