Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 657 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Image Classification | CIFAR-10 Dir(0.5) (test) | 36 | Jun 23, 2026 | ||
| OOD Detection | OpenOOD CIFAR10 Near-OOD | 36 | May 27, 2026 | ||
| LLM-as-a-Judge | RewardBench 1.0 (test) | 36 | Feb 26, 2026 | ||
| LLM-as-a-Judge Evaluation Consistency | RewardBench | 36 | Feb 26, 2026 | ||
| Medical Knowledge Evaluation | MMedbench English subset (val) | 36 | Feb 26, 2026 | ||
| Mathematical Reasoning | SVAMP (val) | 36 | Feb 26, 2026 | ||
| General Reasoning | Big-Bench Hard (BBH) (val) | 36 | Feb 26, 2026 | ||
| Node Classification | CoraFull 5-way 3-shot (test) | 36 | May 26, 2026 | ||
| Natural Language Understanding | ARC Easy | 36 | May 21, 2026 | ||
| Language Modeling | Book3 | 36 | Feb 26, 2026 | ||
| Single Image Super-Resolution | Set14 x2 (test) | 36 | May 19, 2026 | ||
| Disease diagnosis | ODIR 21 (test) | 36 | Feb 26, 2026 | ||
| Disease diagnosis | CXR 20 (test) | 36 | Feb 26, 2026 | ||
| Image Clustering | ImageNet-1K | 36 | May 14, 2026 | ||
| Image Classification | PathMNIST v1 (test) | 36 | Feb 26, 2026 | ||
| Image Classification | CIFAR-100 | 36 | Feb 26, 2026 | ||
| 3D Image Classification | MedMNIST 3D v2 (test) | 36 | Mar 5, 2026 | ||
| Machine-generated text detection | Grover (test) | 36 | Feb 26, 2026 | ||
| Industrial Image Anomaly Detection | BTAD (test) | 36 | Feb 26, 2026 | ||
| Question Answering | SciQ (test) | 36 | Jul 3, 2026 | ||
| Open-domain Question Answering | WebQuestions (test) | 36 | Feb 26, 2026 | ||
| Image Super-Resolution | RealLR200 | 36 | Jun 30, 2026 | ||
| Backdoor Re-activation Attack | CIFAR-10 (test) | 36 | Feb 26, 2026 | ||
| Traveling Salesperson Problem | TSP n=100 (train) | 36 | Jun 11, 2026 | ||
| Point Cloud Filtering | PUNet 50K Dense Laplace noise (synthetic) | 36 | May 27, 2026 |