Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1981 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Sequence Classification | Bit-stream XOR Equidistant encoding (test) | 18 | Feb 26, 2026 | ||
| Image Classification | ImageNet1K 1.0 (train val) | 18 | Feb 26, 2026 | ||
| Tensor Completion | Increasing order nonnegative tensors synthetic n = 10,000 samples | 18 | Feb 26, 2026 | ||
| Temporal Point Process modeling | Wiki real-world (test) | 18 | Feb 26, 2026 | ||
| Point Cloud Classification | Synthetic Point Clouds Gaussian Noise η=0.1 | 18 | Feb 26, 2026 | ||
| Point Cloud Classification | Synthetic Point Clouds Gaussian Noise η=0.05 | 18 | Feb 26, 2026 | ||
| Subspace Clustering | Extended Yale B (2 Subjects) | 18 | Feb 26, 2026 | ||
| Causal Discovery | Double Pendulum Simulated (5 folds) | 18 | Feb 26, 2026 | ||
| Image Reconstruction | MNIST (test) | 18 | Jul 3, 2026 | ||
| Band gap prediction | Materials Project (test) | 18 | Feb 26, 2026 | ||
| Link Prediction | USAir (test) | 18 | Feb 26, 2026 | ||
| Conformal Prediction | meps 21 (test) | 18 | Feb 26, 2026 | ||
| Text Classification | 20ng (test) | 18 | Feb 26, 2026 | ||
| Knowledge Editing | UnKEBench Paraphrased questions (Para.) | 18 | Feb 26, 2026 | ||
| Knowledge Editing | UnKEBench Original questions | 18 | Feb 26, 2026 | ||
| Prompt Injection Defense | Indirect Prompt Injection Tail 1.0 | 18 | Feb 26, 2026 | ||
| Prompt Injection Defense | Indirect Prompt Injection Middle 1.0 | 18 | Feb 26, 2026 | ||
| Prompt Injection Defense | Indirect Prompt Injection Head 1.0 | 18 | Feb 26, 2026 | ||
| Concept Prediction | Derm7pt | 18 | Jun 16, 2026 | ||
| Multimodal Machine Unlearning | SAFEERASER Model Utility v1.0 (general set) | 18 | Feb 26, 2026 | ||
| Multimodal Machine Unlearning | SAFEERASER Generality v1.0 (test) | 18 | Feb 26, 2026 | ||
| Multimodal Machine Unlearning | SAFEERASER Efficacy v1.0 (forget set) | 18 | Feb 26, 2026 | ||
| 3D Object Classification | ModelNet40 8k P v1 | 18 | Feb 26, 2026 | ||
| Reflective Object Reconstruction | Shiny Blender | 18 | Mar 23, 2026 | ||
| Faithfulness Measurement | MHC | 18 | Feb 26, 2026 |