Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1528 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Video jailbreaking | VIDEOSAFETYBENCH | 20 | Jul 1, 2026 | ||
| Object Detection | Cityscapes to Foggy Cityscapes (C2F) v1 | 20 | Jul 1, 2026 | ||
| Object Classification | ModelNet40 | 20 | Jul 1, 2026 | ||
| Translation | Translation | 20 | Jul 1, 2026 | ||
| Few-shot classification | CelebA Random meta (test) | 20 | Jun 30, 2026 | ||
| Few-shot classification | CelebA-Hair meta (test) | 20 | Jun 30, 2026 | ||
| Few-shot classification | MPI3D Hard | 20 | Jun 30, 2026 | ||
| Few-shot classification | MPI3D Easy | 20 | Jun 30, 2026 | ||
| Few-shot classification | Causal3D | 20 | Jun 30, 2026 | ||
| Few-shot classification | Shapes3D | 20 | Jun 30, 2026 | ||
| Few-shot classification | SmallNORB | 20 | Jun 30, 2026 | ||
| Surface Normal Estimation | ScanNet | 20 | Jul 8, 2026 | ||
| Natural language to strategic temporal logic translation | NL-to-ATL translation (test) | 20 | Jun 30, 2026 | ||
| Adversarial Attack Detection | Adversarial Attack Detection (test) | 20 | Jun 30, 2026 | ||
| Knowledge Retrieval and Integration | KR1 protocol (in-distribution) | 20 | Jun 30, 2026 | ||
| Free-form Captioning Hallucination Evaluation | CHAIR | 20 | Jun 30, 2026 | ||
| Node Classification | PubMed | 20 | Jun 30, 2026 | ||
| Node Classification | CiteSeer | 20 | Jun 30, 2026 | ||
| Instruction Following | UnNI (OOD) | 20 | Jun 30, 2026 | ||
| Instruction Following | S-NI (OOD) | 20 | Jun 30, 2026 | ||
| Instruction Following | VicunaEval (OOD) | 20 | Jun 30, 2026 | ||
| Instruction Following | SelfInst (OOD) | 20 | Jun 30, 2026 | ||
| Ranking | Jester Dataset | 20 | Jun 30, 2026 | ||
| Image Classification | CIFAR-10 Structure | 20 | Jun 30, 2026 | ||
| Image Classification | MNIST (Structure) | 20 | Jun 30, 2026 |