Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1390 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Polyp Segmentation | Colonoscopy Datasets Average | 22 | Feb 26, 2026 | ||
| Image Classification | MedMNIST OrganAMNIST (test) | 22 | Apr 3, 2026 | ||
| Point Tracking | RoboTAP | 22 | Mar 27, 2026 | ||
| OOD Detection | CIFAR-100 | 22 | Feb 26, 2026 | ||
| Semantic Segmentation | PASCAL VOC PAS-20 | 22 | Feb 26, 2026 | ||
| 3D semantic occupancy prediction | SurroundOcc-nuScenes night scenario (val) | 22 | Feb 26, 2026 | ||
| Object Detection | VisDrone | 22 | Apr 6, 2026 | ||
| Video Object Segmentation | MOSE SAM2.1-B+ (val) | 22 | Feb 26, 2026 | ||
| Video Object Segmentation | DAVIS 2017 SAM2.1-B+ (val) | 22 | Feb 26, 2026 | ||
| Video Object Segmentation | SA-V SAM2.1-B+ (val) | 22 | Feb 26, 2026 | ||
| Video Object Segmentation | SA-V SAM2.1-B+ (test) | 22 | Feb 26, 2026 | ||
| Grounding | OSworld G-R | 22 | Jun 23, 2026 | ||
| Underwater Image Enhancement | UIEB 9 | 22 | Feb 26, 2026 | ||
| Underwater Image Enhancement | SUIM-E 28 | 22 | Feb 26, 2026 | ||
| Multimodal Perception | VStar | 22 | Jun 9, 2026 | ||
| Prompt Injection Defense | AgentDojo | 22 | Jun 9, 2026 | ||
| Encrypted LLM Inference | 128 token prompt | 22 | May 6, 2026 | ||
| Text Anonymization | SynthPAI | 22 | Feb 26, 2026 | ||
| Adversarial Evasion Attack | MGT Academic STEM | 22 | Feb 26, 2026 | ||
| Adversarial Evasion Attack | MGT-Academic Social Science | 22 | Feb 26, 2026 | ||
| Adversarial Evasion Attack | MGT-Academic Humanity | 22 | Feb 26, 2026 | ||
| Jailbreak Attack | Jailbreak Attack Suite | 22 | Apr 2, 2026 | ||
| Secure Code Generation | CWEval | 22 | Mar 4, 2026 | ||
| Reading Comprehension | Belebele EN | 22 | Mar 6, 2026 | ||
| Text-to-OverpassQL | OverpassNL (val) | 22 | Feb 26, 2026 |