Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1634 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Peg Insertion | VLA Backdoor Evaluation Tasks | 20 | Feb 26, 2026 | ||
| Button Pressing | VLA Backdoor Evaluation Tasks | 20 | Feb 26, 2026 | ||
| Drawer Opening | VLA Backdoor | 20 | Feb 26, 2026 | ||
| Pick-and-Place | VLA Backdoor Evaluation Tasks | 20 | Feb 26, 2026 | ||
| Robotic Manipulation (Long) | LIBERO Long 1.0 (test) | 20 | Feb 26, 2026 | ||
| Multi-turn Jailbreak Defense | MTJ-Pro | 20 | Feb 26, 2026 | ||
| Adversarial Attack Misdirection | MTJ-Pro (test) | 20 | Feb 26, 2026 | ||
| Code Repair | CodeFix | 20 | Feb 26, 2026 | ||
| Image Classification | Cifar-10 (test) | 20 | Feb 26, 2026 | ||
| Model Lineage Attestation | Caltech101 -> Caltech101 -> CIFAR100 | 20 | Feb 26, 2026 | ||
| Secure Inference | MNIST (test) | 20 | Feb 26, 2026 | ||
| DDoS Attack Classification | CICIOT 2023 | 20 | Feb 26, 2026 | ||
| DDoS Attack Classification | CIC-IoT 2023 | 20 | Feb 26, 2026 | ||
| Steganographic secret extraction | WikiText-103 W (test) | 20 | Feb 26, 2026 | ||
| Federated Learning Classification | MNIST (test) | 20 | Feb 26, 2026 | ||
| Image Classification | MNIST ViT-Lite variant (test) | 20 | Feb 26, 2026 | ||
| Federated Image Classification | Fashion-MNIST (test) | 20 | Feb 26, 2026 | ||
| Masked Language Modeling Fine-tuning | arXiv (fine-tuning) | 20 | Feb 26, 2026 | ||
| Privacy Amplification | CIFAR-10 (train) | 20 | Feb 26, 2026 | ||
| Partial code vulnerability detection | SVEN | 20 | Feb 27, 2026 | ||
| Unknown attack detection | IoT-23 | 20 | Feb 26, 2026 | ||
| Unknown attack detection | CICIoT 2023 | 20 | Feb 26, 2026 | ||
| Speculative decoding evaluation | OOD Mean | 20 | Feb 26, 2026 | ||
| Multilingual mathematical reasoning | MGSM | 20 | Feb 26, 2026 | ||
| Long-context retrieval | NIAH multivalue | 20 | Feb 26, 2026 |