Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 218 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Near-OOD Detection | CIFAR-10 | 71 | Apr 15, 2026 | ||
| 3D Shape Completion | ShapeNet synthetic objects (unseen categories) | 71 | May 27, 2026 | ||
| Image Classification | ImageNet I-Squawk (test) | 71 | May 21, 2026 | ||
| Question Answering | Musique | 71 | Jun 1, 2026 | ||
| Category Discovery | Stanford Cars | 71 | Apr 14, 2026 | ||
| Commonsense Question Answering | CSQA | 71 | May 15, 2026 | ||
| Text-based Visual Question Answering | TextVQA VQAT | 71 | Jun 23, 2026 | ||
| Symbolic Regression | SRBench black-box (test) | 71 | May 27, 2026 | ||
| Table Question Answering | NQTables (test) | 71 | Apr 23, 2026 | ||
| Multi-hop Question Answering | 2WikiQA (test) | 71 | May 12, 2026 | ||
| Gradient Inversion Attack | CIFAR-10 | 71 | Jun 4, 2026 | ||
| Text-to-Image Generation | HPS v2 | 71 | Jun 8, 2026 | ||
| Image Captioning | CHAIR | 71 | Jun 30, 2026 | ||
| Robotic Manipulation | Calvin ABC-D | 71 | May 13, 2026 | ||
| Video Question Answering | Video-MME Long | 71 | Jul 7, 2026 | ||
| Image Classification | OxfordPets | 71 | May 26, 2026 | ||
| Text Classification | SST2 | 71 | Mar 5, 2026 | ||
| Model Editing | zsRE | 71 | Apr 7, 2026 | ||
| General Knowledge | MMLU (test) | 71 | Jul 3, 2026 | ||
| Agentic Coding | SWE-bench Verified | 71 | Jun 16, 2026 | ||
| Continual Learning | Standard CL Benchmark | 71 | May 12, 2026 | ||
| Multimodal Model Evaluation | MME | 71 | May 29, 2026 | ||
| Jailbreak Robustness | StrongREJECT | 71 | May 12, 2026 | ||
| Video reasoning | MMVU | 71 | Jul 7, 2026 | ||
| Image Quality Assessment | CLIVE | 71 | Jun 16, 2026 |