Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1485 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Closed-loop simulation | NeuroNCAP | 21 | Mar 9, 2026 | ||
| Long Video Understanding | MLVU multiple-choice task | 21 | Feb 26, 2026 | ||
| Image Captioning | RSITMD | 21 | Mar 11, 2026 | ||
| Point Cloud Classification | ModelNet40 10-way 20-shot | 21 | Feb 26, 2026 | ||
| Point Cloud Classification | ModelNet40 10-way 10-shot | 21 | Feb 26, 2026 | ||
| Point Cloud Classification | ModelNet40 5-way 20-shot | 21 | Feb 26, 2026 | ||
| Point Cloud Classification | ModelNet40 5-way 10-shot | 21 | Feb 26, 2026 | ||
| Point Cloud Object Recognition | ScanObjectNN OBJ_ONLY (test) | 21 | Feb 26, 2026 | ||
| Object Detection | FireRescue dataset (test) | 21 | Feb 26, 2026 | ||
| Polygonal Surface Reconstruction | ABC-plane | 21 | Feb 26, 2026 | ||
| Deep Clustering | CIFAR-100 | 21 | Feb 26, 2026 | ||
| Semantic Segmentation | EarthVLSet (test) | 21 | Feb 26, 2026 | ||
| Multiple-choice Visual Question Answering | EarthVLSet | 21 | Feb 26, 2026 | ||
| Visual-Semantic Understanding | CII-Bench | 21 | Feb 26, 2026 | ||
| Humor Detection | YesBut | 21 | Feb 26, 2026 | ||
| Deep Semantic Inference | DeepEval | 21 | Feb 26, 2026 | ||
| Explicit Content Unlearning | I2P | 21 | May 18, 2026 | ||
| 3D object selection | LERF-OVS | 21 | May 7, 2026 | ||
| Multi-image Grounding | MIG-Bench (test) | 21 | Apr 14, 2026 | ||
| Video Action Retrieval | SOVABench Intra-pair 1.0 | 21 | Feb 26, 2026 | ||
| Video Action Retrieval | SOVABench Inter-pair 1.0 | 21 | Feb 26, 2026 | ||
| 3D Segmentation | NVOS (held-out val view) | 21 | Feb 26, 2026 | ||
| Leaf Disease Classification | PlantDoc | 21 | Apr 30, 2026 | ||
| Adversarial Purification | CelebA-HQ | 21 | Feb 26, 2026 | ||
| text-to-video generation | VBench HunyuanVideo (test) | 21 | Feb 26, 2026 |