Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1783 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Text-to-Speech | VCTK | 19 | Apr 14, 2026 | ||
| Graph Regression | QM9 | 19 | Mar 19, 2026 | ||
| Anomaly Detection | BTCV + LITS | 19 | Mar 4, 2026 | ||
| Change Detection | S2Looking 35 | 19 | Feb 26, 2026 | ||
| Change Detection | LEVIR-CD 34 | 19 | Feb 26, 2026 | ||
| Image Editing | GEdit-Bench-EN Intersection subset v1.0 | 19 | Mar 4, 2026 | ||
| Machine Translation | IWSLT (test) | 19 | Feb 26, 2026 | ||
| Dexterous Hand Control | Adroit | 19 | Mar 5, 2026 | ||
| Visual Question Answering | CulturalVQA (test) | 19 | Feb 26, 2026 | ||
| Chat | MT-Bench 1.0 (test) | 19 | Feb 26, 2026 | ||
| Class-Conditional Video Generation | UCF101 | 19 | Feb 26, 2026 | ||
| Attributed Text Generation | ELI5 | 19 | Feb 26, 2026 | ||
| Attributed Text Generation | QAMPARI | 19 | Feb 26, 2026 | ||
| Attributed Text Generation | ASQA | 19 | Feb 26, 2026 | ||
| Video Forgery Detection | DVF (test) | 19 | Apr 7, 2026 | ||
| Novel View Synthesis | Mip-NeRF360 official (test) | 19 | Feb 26, 2026 | ||
| Object Hallucination Probing | GQA POPE (Adversarial) | 19 | Apr 10, 2026 | ||
| Pronoun Resolution | XWinograd | 19 | May 12, 2026 | ||
| Image Classification | ImageNette 10 cls, 9.5k (test) | 18 | Jul 9, 2026 | ||
| Segmentation | OCTA-500 6 mm | 18 | Jul 9, 2026 | ||
| Dialect Bias Evaluation | REAL-AAE | 18 | Jul 9, 2026 | ||
| Zero-shot Task Performance | 0-shot6 (test) | 18 | Jul 9, 2026 | ||
| Motor Imagery Classification | BCI Competition 2a IV | 18 | Jul 9, 2026 | ||
| Synthetic Image Detection | AIGCDetectionBenchmark | 18 | Jul 8, 2026 | ||
| Synthetic Image Detection | DDA-COCO | 18 | Jul 8, 2026 |