Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 35 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| 3D Semantic Segmentation | ScanNet v2 (val) | 230 | Jun 25, 2026 | ||
| Visual Grounding | RefCOCO+ (testB) | 230 | Jul 3, 2026 | ||
| Mathematical Problem Solving | MATH | 229 | Mar 10, 2026 | ||
| Compressive Sensing Recovery | Set11 | 229 | May 12, 2026 | ||
| Point Cloud Classification | ModelNet40 (test) | 229 | Jun 26, 2026 | ||
| Face Recognition | LFW | 229 | Jun 1, 2026 | ||
| Generalized Zero-Shot Learning | SUN | 229 | Mar 24, 2026 | ||
| Text-to-Video Retrieval | MSVD (test) | 229 | Jun 19, 2026 | ||
| Visual Place Recognition | Tokyo24/7 | 229 | Jun 2, 2026 | ||
| Regression | Superconduct | 228 | Jul 7, 2026 | ||
| Multimodal Math Reasoning | WeMath | 228 | Jun 11, 2026 | ||
| Mathematical Reasoning | Minerva Math | 228 | Apr 21, 2026 | ||
| Generalized Category Discovery | Stanford Cars | 228 | Jul 2, 2026 | ||
| Image Classification | Caltech101 | 228 | Mar 27, 2026 | ||
| Topic Classification | AG-News | 228 | Jun 26, 2026 | ||
| Multi-Object Tracking | MOT16 (test) | 228 | Feb 26, 2026 | ||
| Novel View Synthesis | Mip-NeRF 360 (test) | 228 | Jun 30, 2026 | ||
| Domain Generalization | DomainNet | 228 | Jul 3, 2026 | ||
| Unconditional Text Generation | OpenWebText | 227 | Jun 24, 2026 | ||
| Mathematical Reasoning | AIME 2025 | 227 | Feb 26, 2026 | ||
| Question Answering | Bamboogle | 227 | Jun 29, 2026 | ||
| Time-series forecasting | Exchange | 227 | Jun 12, 2026 | ||
| 3D Shape Classification | ModelNet40 (test) | 227 | Feb 26, 2026 | ||
| Person Re-identification | CUHK03 (Detected) | 227 | Apr 7, 2026 | ||
| Graph Classification | PROTEINS (test) | 227 | Jul 7, 2026 |