Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1374 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Computer Graphics Quality Assessment | R4-CGQA (test) | 22 | Mar 12, 2026 | ||
| ASD diagnosis | ABIDE NYU center (test) | 22 | Mar 11, 2026 | ||
| BD diagnosis | Private cohort BD (test) | 22 | Mar 11, 2026 | ||
| MDD diagnosis | Private cohort MDD (test) | 22 | Mar 11, 2026 | ||
| Multimodal Audio Reasoning | MMAR | 22 | Mar 11, 2026 | ||
| Science Knowledge | SciQ | 22 | May 19, 2026 | ||
| Deepfake Detection | DF40 (cross-manipulation) | 22 | Mar 11, 2026 | ||
| Multiple Choice Question Answering | MC Benchmarks | 22 | Mar 11, 2026 | ||
| Image Deraining | Rain1400 | 22 | May 14, 2026 | ||
| Activity Recognition | RoboFiSense V1 (test) | 22 | Mar 11, 2026 | ||
| Activity Recognition | RoboFiSense V2 (test) | 22 | Mar 11, 2026 | ||
| Activity Recognition | RoboFiSense V3 (test) | 22 | Mar 11, 2026 | ||
| Medical Visual Question Answering | MIMIC-CXR-VQA (test) | 22 | Apr 21, 2026 | ||
| Speech Enhancement | Speech Enhancement (SE) Task (test) | 22 | Mar 10, 2026 | ||
| Broad-concept removal | I2P | 22 | May 19, 2026 | ||
| n-ary drug combination extraction | DrugComb (test) | 22 | Mar 10, 2026 | ||
| Object Detection | VOC Dark low-light (val) | 22 | Mar 10, 2026 | ||
| Object Detection | RTTS v1 (test) | 22 | Mar 10, 2026 | ||
| Object Detection | VOC haze (val) | 22 | Mar 10, 2026 | ||
| Omnidirectional Image Understanding | ODI-Bench close-ended 1.0 | 22 | Mar 10, 2026 | ||
| Grasp Success Prediction | Grasp dataset | 22 | Mar 10, 2026 | ||
| Infrared-Visible Image Fusion | KAIST | 22 | Mar 10, 2026 | ||
| Infrared-Visible Image Fusion | FLIR | 22 | Mar 10, 2026 | ||
| End-to-end motion planning | nuScenes | 22 | Apr 7, 2026 | ||
| LLM Instruction Tuning | MMLU | 22 | May 12, 2026 |