Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 535 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Concept Erasure | 39 NLP settings (13 LLMs x 3 concepts: sycophancy, gender, safety) | 40 | Jul 7, 2026 | ||
| Sharp Novel View Synthesis | PRISM3D-E Benchmark Synthetic (All Scenes) | 40 | Jul 7, 2026 | ||
| Molecule Property Prediction | DrugOOD-EC50 (assay) | 40 | Jul 7, 2026 | ||
| Molecule Property Prediction | DrugOOD-IC50 (assay) | 40 | Jul 7, 2026 | ||
| Image Generation | CIFAR-10 (test) | 40 | Jul 7, 2026 | ||
| Keyword Spotting | GSC v2 | 40 | Jul 3, 2026 | ||
| Document Retrieval | HotpotQA | 40 | Jul 3, 2026 | ||
| Object Detection | PDM | 40 | Jul 2, 2026 | ||
| Camera Pose Estimation | TerraSky3D (Individual Scenes) | 40 | Jul 2, 2026 | ||
| Novel View Synthesis | Mip-NeRF 360 standard 1 (test) | 40 | Jul 2, 2026 | ||
| Medical Visual Question Answering | PMC-VQA | 40 | Jul 1, 2026 | ||
| Automatic Modulation Recognition | AMR Dataset (test) | 40 | Jul 1, 2026 | ||
| Signal Scheme Recognition | Signal Scheme Recognition (SSR) dataset | 40 | Jul 1, 2026 | ||
| Skill Selection | Production Agent | 40 | Jul 1, 2026 | ||
| Classification | controlled 784-feature benchmark (test) | 40 | Jul 1, 2026 | ||
| Tabular Classification | xdomain13 (test) | 40 | Jun 30, 2026 | ||
| Classification | CUMIDA-42 Random-100 feature arm | 40 | Jun 30, 2026 | ||
| Gene-expression classification | CUMIDA-42 | 40 | Jun 30, 2026 | ||
| Spatial Relationship Accuracy | DA-2K | 40 | Jun 30, 2026 | ||
| Spatial Relationship Accuracy | MD-3k Same | 40 | Jun 30, 2026 | ||
| Spatial Relationship Accuracy | MD-3k Reverse | 40 | Jun 30, 2026 | ||
| Estrogen Receptor Status Prediction | TCGA-BRCA | 40 | Jun 30, 2026 | ||
| Disease Specific Survival Prediction | TCGA-BRCA | 40 | Jun 30, 2026 | ||
| Generative Text Steganography | SHAKESPEARE | 40 | Jun 29, 2026 | ||
| Generative Text Steganography | IMDB (test) | 40 | Jun 29, 2026 |