Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 2696 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Action Recognition | ShuttleSet fixed-width strategy 25 classes | 14 | Apr 1, 2026 | ||
| Action Recognition | ShuttleSet 35 classes fixed-width strategy (test) | 14 | Apr 1, 2026 | ||
| Recommendation | food | 14 | Apr 10, 2026 | ||
| Deepfake Detection | DF40 and FFHQ unseen generators | 14 | Apr 1, 2026 | ||
| Detection | Unseen Datasets Average | 14 | Apr 1, 2026 | ||
| Attribution | Unseen Datasets Average | 14 | Apr 1, 2026 | ||
| Attribution | DFDC | 14 | Apr 1, 2026 | ||
| Attribution | Celeb-DF | 14 | Apr 1, 2026 | ||
| Deepfake Detection | Unseen Advanced Generators VAE, HART, FLUX | 14 | Apr 1, 2026 | ||
| Deepfake Attribution | Unseen Advanced Generators VAE, HART, FLUX | 14 | Apr 1, 2026 | ||
| Infrared Small Target Detection | NUDT-SIRST | 14 | Apr 1, 2026 | ||
| Infrared Small Target Detection | IRSTD-1k | 14 | Apr 1, 2026 | ||
| Emotion Classification | DREAMER (subject-independent) | 14 | Jul 2, 2026 | ||
| Prompt Optimization Evaluation | HelpSteer2 | 14 | Apr 1, 2026 | ||
| Prompt Optimization Evaluation | HelpSteer 1 | 14 | Apr 1, 2026 | ||
| Visual Question Answering | PathVQA | 14 | Jun 11, 2026 | ||
| Object Detection | Mixed multimodality medical dataset 1.0 (test) | 14 | Apr 1, 2026 | ||
| Sequential Knowledge Editing | CounterFact larger | 14 | Apr 1, 2026 | ||
| Sequential Knowledge Editing | CounterFact top | 14 | Apr 1, 2026 | ||
| Anonymization | Indoor | 14 | Mar 31, 2026 | ||
| Anonymization | Cal101 | 14 | Mar 31, 2026 | ||
| Image Retrieval | In-domain (ID) Split | 14 | Mar 31, 2026 | ||
| Image Retrieval | SOP-1k | 14 | Mar 31, 2026 | ||
| Image Retrieval | RP2K | 14 | Mar 31, 2026 | ||
| Image Retrieval | Prod1M | 14 | Apr 16, 2026 |