Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1720 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Surface Normals estimation | NYUD v2 | 19 | Jun 16, 2026 | ||
| Text Generation | Open Web Text (OWT) (val) | 19 | Mar 23, 2026 | ||
| Visual Question Answering | Path-VQA YorN | 19 | Jun 9, 2026 | ||
| Content preservation | MS-COCO 30K | 19 | Apr 21, 2026 | ||
| Multi-objective Capacitated Vehicle Routing Problem | MOCVRP 100 | 19 | Mar 20, 2026 | ||
| Multi-objective Capacitated Vehicle Routing Problem | MOCVRP 50 | 19 | Mar 20, 2026 | ||
| Multi-objective Capacitated Vehicle Routing Problem | MOCVRP20 | 19 | Mar 20, 2026 | ||
| Node Classification | Pubmed (test) | 19 | Mar 30, 2026 | ||
| Surgical Scene Segmentation | CholecSeg 8k (OOD) | 19 | Mar 20, 2026 | ||
| Context Management | Long-context (test) | 19 | Mar 20, 2026 | ||
| Plan Generation | 60-task evaluation suite 10 domains | 19 | Mar 20, 2026 | ||
| Language Modeling | Fineweb 100B | 19 | May 20, 2026 | ||
| Semantic Segmentation | RADIal (test) | 19 | Mar 19, 2026 | ||
| Video Question Answering | LongVideoBench (standard) | 19 | Jul 2, 2026 | ||
| Success Rate Evaluation | VLABench | 19 | Mar 25, 2026 | ||
| Emotion Recognition | SEED-IV (single-session) | 19 | Mar 19, 2026 | ||
| Linear Regression | Superconductivity 20 MCAR injected (test) | 19 | Mar 19, 2026 | ||
| Image Classification | CIFAR-100 Flip label noise (test) | 19 | Mar 19, 2026 | ||
| Image Classification | CIFAR-10 Flip label noise (test) | 19 | Mar 19, 2026 | ||
| Video Classification | HMDB51 112x112 (test) | 19 | Mar 19, 2026 | ||
| Video Classification | MiniUCF 112x112 (test) | 19 | Mar 19, 2026 | ||
| Graph regression | CEP | 19 | May 26, 2026 | ||
| Classification | Iris | 19 | Jun 15, 2026 | ||
| Image Restoration | RDRF (test) | 19 | Mar 18, 2026 | ||
| Science Question Answering | ARC Challenge | 19 | Mar 26, 2026 |