Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1881 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Graph Anomaly Detection | T-Social | 18 | Mar 10, 2026 | ||
| Aspect-Based Sentiment Analysis | Laptop14 | 18 | Mar 10, 2026 | ||
| Temporal Link Prediction | ICEWS14 filtered (test) | 18 | Mar 10, 2026 | ||
| Judgment Bias Evaluation | JudgeBiasBench (test) | 18 | Mar 10, 2026 | ||
| Scene Graph Generation | PSG (test) | 18 | Jun 5, 2026 | ||
| Object Detection | Glottis | 18 | Mar 10, 2026 | ||
| Object Tracking | SatSOT | 18 | Apr 24, 2026 | ||
| Topic Classification | AGNEWS | 18 | Mar 10, 2026 | ||
| Semantic Segmentation | NYU v2 | 18 | Mar 10, 2026 | ||
| Node Classification | Cornell | 18 | Mar 10, 2026 | ||
| Node Classification Robustness Certification | CiteSeer | 18 | Mar 10, 2026 | ||
| Tabular Classification | 53 classification datasets (unseen) | 18 | Mar 10, 2026 | ||
| Atomic Memory Recall | Super-Natural Instructions (SNI) (test) | 18 | Mar 10, 2026 | ||
| Cause to Effect | e-CARE + RedPajama XL | 18 | Mar 10, 2026 | ||
| Cause to Effect | e-CARE | 18 | Mar 10, 2026 | ||
| Machine Unlearning | ImageNet Retain set | 18 | May 15, 2026 | ||
| Regression | Power Plant | 18 | Mar 10, 2026 | ||
| Regression | Concrete | 18 | Mar 10, 2026 | ||
| Classification | NHANES | 18 | Mar 10, 2026 | ||
| Classification | AIDS | 18 | Mar 10, 2026 | ||
| Video Temporal Grounding | Charades-STA g43_s7 (test) | 18 | Mar 10, 2026 | ||
| Image Reconstruction | E-MNIST | 18 | Mar 10, 2026 | ||
| Protein sequence design | CATH 4.3 (test) | 18 | Mar 10, 2026 | ||
| Image Classification | ImageNet-C | 18 | Jul 1, 2026 | ||
| Image Classification | MNIST (test) | 18 | Mar 10, 2026 |