Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 925 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Image Classification | CIFAR-10 Corruption v1 | 28 | Jul 7, 2026 | ||
| Membership Inference Attack | OpenForensics | 28 | Jul 7, 2026 | ||
| Membership Inference Attack | GTSRB | 28 | Jul 7, 2026 | ||
| Membership Inference Attack | CINIC10 (CN10) | 28 | Jul 7, 2026 | ||
| Membership Inference Attack | CIFAR10 | 28 | Jul 7, 2026 | ||
| Facial Privacy Protection | VGGFace2 | 28 | Jul 3, 2026 | ||
| Multi-hop Question Answering | 2WikiMultihopQA | 28 | Jul 2, 2026 | ||
| Multi-hop Question Answering | MuSiQue | 28 | Jul 2, 2026 | ||
| Multi-hop Question Answering | HotpotQA | 28 | Jul 2, 2026 | ||
| Robotic Grasping | Real robot platform (test) | 28 | Jul 2, 2026 | ||
| 3D Scene Graph Generation | 3DSSG (test) | 28 | Jul 9, 2026 | ||
| Support Recovery | Synthetic linear regression data | 28 | Jul 2, 2026 | ||
| Error detection | Unanswerability hallucination detection benchmarks (Average) | 28 | Jul 1, 2026 | ||
| Open-ended multimodal understanding | Open-ended multimodal understanding benchmarks Average | 28 | Jul 1, 2026 | ||
| Prompt Injection Mitigation | 17 Injection Types Appendix E | 28 | Jul 1, 2026 | ||
| Image Classification | UCF101 | 28 | Jul 1, 2026 | ||
| Destination Prediction | Porto | 28 | Jul 7, 2026 | ||
| Destination Prediction | Beijing | 28 | Jul 7, 2026 | ||
| Therapeutic Quality Judging | Therapeutic quality evaluation dataset | 28 | Jul 1, 2026 | ||
| Tabular Classification and Regression | TALENT Tiny | 28 | Jun 30, 2026 | ||
| Material Decomposition | Breast spectral CT dataset | 28 | Jun 30, 2026 | ||
| Question Answering | TriviaQA (test) | 28 | Jun 30, 2026 | ||
| Question Answering | NQ (test) | 28 | Jun 30, 2026 | ||
| Question Answering | GAIA (test) | 28 | Jun 30, 2026 | ||
| Question Answering | FRAMES (test) | 28 | Jun 30, 2026 |