Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 351 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Jailbreak Defense | ReNeLLM | 53 | Jun 15, 2026 | ||
| WSI Classification | NSCLC | 53 | Mar 4, 2026 | ||
| Video Question Answering | VideoMME Medium | 53 | Apr 21, 2026 | ||
| Semantic Segmentation | Pascal VOC 1/16 labeled 2012 (train) | 53 | Feb 26, 2026 | ||
| Inference Acceleration | Spec-Bench | 53 | May 13, 2026 | ||
| Instructive image editing | MagicBrush (test) | 53 | May 14, 2026 | ||
| Infrared-Visible Image Fusion | RoadScene (test) | 53 | Jun 16, 2026 | ||
| Novel View Synthesis | LLFF 3-view (test) | 53 | Jun 30, 2026 | ||
| Point Tracking | TAP-Vid Kinetics (First) | 53 | Apr 15, 2026 | ||
| Optic Cup / Disc Segmentation | Fundus Domain 4 | 53 | Apr 24, 2026 | ||
| Optic Cup / Disc Segmentation | Fundus Domain 3 | 53 | Apr 24, 2026 | ||
| Optic Cup / Disc Segmentation | Fundus Domain 2 | 53 | Apr 24, 2026 | ||
| Few-shot Semantic Segmentation | CD-FSS 1-shot 1.0 (test) | 53 | Jun 24, 2026 | ||
| Unconditional Image Generation | FFHQ 64x64 (test) | 53 | Mar 13, 2026 | ||
| Tool-use | ToolBench | 53 | May 15, 2026 | ||
| Out-of-Distribution Detection | CIFAR100 (ID) SVHN (OOD) | 53 | Jul 8, 2026 | ||
| Text-to-Image Retrieval | COCO 5K (test) | 53 | Jun 1, 2026 | ||
| Time Series Forecasting | Stock | 53 | Jun 18, 2026 | ||
| Audio-Visual Speech Recognition | LRS-3 Babble noise at 0dB SNR (test) | 53 | Jun 5, 2026 | ||
| Emotion Classification | EmoC | 53 | Feb 26, 2026 | ||
| Object Detection | Diverse Weather Dataset (DWD) (test) | 53 | Jul 9, 2026 | ||
| Image Classification | ImageNet (source) | 53 | Jul 8, 2026 | ||
| Text-to-image generation | COCO 2017 (val) | 53 | Jul 7, 2026 | ||
| Offline Reinforcement Learning | D4RL Adroit pen (cloned) | 53 | May 28, 2026 | ||
| Offline Reinforcement Learning | D4RL Adroit pen (human) | 53 | May 28, 2026 |