Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 339 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Question Answering | MuSiQue | 54 | May 29, 2026 | ||
| VLM Pairwise Preference | ArcBench | 54 | Apr 15, 2026 | ||
| Passage Reranking | BRIGHT | 54 | Jun 2, 2026 | ||
| Causal Inference | CounterBench | 54 | May 26, 2026 | ||
| Image Manipulation Localization | CASIA v1 | 54 | Jun 11, 2026 | ||
| Federated Class-Incremental Learning | Tiny-ImageNet 10 tasks (20 classes per task) (test) | 54 | Apr 13, 2026 | ||
| Image Classification | Tiny-ImageNet standard (Forget) | 54 | Apr 10, 2026 | ||
| Image Classification | Tiny-ImageNet standard (Retain) | 54 | Apr 10, 2026 | ||
| Image Classification | CIFAR-100 standard (Forget) | 54 | Apr 10, 2026 | ||
| Image Classification | CIFAR-100 standard (Retain) | 54 | Apr 10, 2026 | ||
| Image Classification | CIFAR-10 standard (Retain) | 54 | Apr 10, 2026 | ||
| Text Classification | SST-2 | 54 | Jun 1, 2026 | ||
| Mathematical Reasoning | MATH 500 | 54 | Apr 10, 2026 | ||
| Math reasoning | MultiArith (test) | 54 | Apr 23, 2026 | ||
| Scientific Reasoning | GPQA Diamond | 54 | Jun 4, 2026 | ||
| Mathematical Reasoning | GSM8K | 54 | Apr 6, 2026 | ||
| Mathematical Reasoning | AIME 25 | 54 | Apr 6, 2026 | ||
| Mathematical Reasoning | AIME 24 | 54 | Apr 6, 2026 | ||
| Approximate Nearest Neighbor Search | SIFT1M | 54 | Jun 11, 2026 | ||
| Time Series Classification | PhysioNet Sepsis (test) | 54 | Jul 2, 2026 | ||
| Membership Inference Attack | DALL·E (test) | 54 | Apr 2, 2026 | ||
| Time-series forecasting | ETTm1 few-shot 10% data | 54 | Apr 15, 2026 | ||
| Deepfake Attribution | DF40 and FFHQ unseen generators | 54 | May 13, 2026 | ||
| Sparse Covariance Matrix Estimation | Sparse Covariance Structure | 54 | Mar 31, 2026 | ||
| Image Classification | CIFAR-10 (test) | 54 | Mar 31, 2026 |