Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 750 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Image Captioning Hallucination Evaluation | COCO Cap Chair | 32 | Jun 26, 2026 | ||
| Object Hallucination Evaluation | POPE | 32 | Jun 26, 2026 | ||
| Visual Question Answering | ESB | 32 | Jun 26, 2026 | ||
| Image Captioning Evaluation | CaptionQA | 32 | Jun 26, 2026 | ||
| Math Reasoning | GSM8K | 32 | Jul 1, 2026 | ||
| Uncertainty quantification | τ2-bench Retail | 32 | Jun 25, 2026 | ||
| Uncertainty quantification | τ2-bench Airline | 32 | Jun 25, 2026 | ||
| Long-Context Generation | PG-19 32K context length | 32 | Jun 25, 2026 | ||
| Long-Context Generation | PG-19 24K context length | 32 | Jun 25, 2026 | ||
| Long-Context Generation | PG-19 16K context length | 32 | Jun 25, 2026 | ||
| Long-Context Generation | PG-19 8K context length | 32 | Jun 25, 2026 | ||
| Camera Relocalization | ScanNet v1 (test) | 32 | Jun 24, 2026 | ||
| Image Classification | reduced-scale ImageNet-1K (test) | 32 | Jun 24, 2026 | ||
| Personalized Federated Learning | CIFAR-10 | 32 | Jun 23, 2026 | ||
| Classification | GTSRB | 32 | Jun 23, 2026 | ||
| Personalized Federated Learning | CIFAR-100 (test) | 32 | Jun 23, 2026 | ||
| Code Generation | HE+ | 32 | Jun 23, 2026 | ||
| Tabular Question Answering | HiTab (val) | 32 | Jun 23, 2026 | ||
| Parameter Identification | Burgers' equation Case 3.3 | 32 | Jun 23, 2026 | ||
| Synthetic Heart Audio Classification | CARDIOFAKE 1.0 (Unseen) | 32 | Jun 23, 2026 | ||
| Synthetic Heart Audio Classification | CARDIOFAKE Seen 1.0 | 32 | Jun 23, 2026 | ||
| Factuality Question Answering | SampleQA | 32 | Jun 23, 2026 | ||
| Time-Series Anomaly Detection | Trend 7.8 | 32 | Jun 23, 2026 | ||
| Time-Series Anomaly Detection | Seasonal 7.7 | 32 | Jun 23, 2026 | ||
| Node Classification Explanation | Tree-grid | 32 | Jun 23, 2026 |