Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 768 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Science Question Answering | Sci-QA | 32 | Mar 30, 2026 | ||
| Multiple Choice Question Answering | UNED-Access Spanish 2024 (test) | 32 | Mar 30, 2026 | ||
| Multiple Choice Question Answering | UNED-Access English 2024 (test) | 32 | Mar 30, 2026 | ||
| Multiple Choice Question Answering | MMLU Spanish (test) | 32 | Mar 30, 2026 | ||
| Multiple Choice Question Answering | MMLU English (test) | 32 | Mar 30, 2026 | ||
| Semantic Segmentation | Cityscapes 500 images (val) | 32 | Mar 27, 2026 | ||
| Utility Preservation | MS-COCO 10K | 32 | May 18, 2026 | ||
| PDE Solving | 2D Allen-Cahn equation a=15 | 32 | Mar 27, 2026 | ||
| Traffic Signal Control | Hangzhou D_HZ(2) | 32 | Apr 8, 2026 | ||
| Continuous Subjective Prediction | A3-Dataset | 32 | Mar 26, 2026 | ||
| Icon Grounding | A3-Dataset | 32 | Mar 26, 2026 | ||
| Aesthetic Classification | A3-Dataset | 32 | Mar 26, 2026 | ||
| AI-generated image detection | WildFake (All) | 32 | Mar 25, 2026 | ||
| Feature Space Preservation | C4 | 32 | Mar 25, 2026 | ||
| Feature Space Preservation | WikiText-2 | 32 | Mar 25, 2026 | ||
| Language Modeling | C4 | 32 | Mar 25, 2026 | ||
| Weather Report Generation | WeatherTGD Dataset | 32 | Mar 24, 2026 | ||
| 3D Anomaly Detection | Anomaly-ShapeNet | 32 | Jun 25, 2026 | ||
| Multi-Task Learning | PASCAL-Context (val) | 32 | Apr 28, 2026 | ||
| Component-level attribution | IOI | 32 | Mar 23, 2026 | ||
| Classification | Monk | 32 | Apr 10, 2026 | ||
| Collaborative Perception | V2XSet (test) | 32 | Mar 23, 2026 | ||
| Collaborative Perception | OPV2V (test) | 32 | Mar 23, 2026 | ||
| Medication Recommendation | MIMIC-IV | 32 | Jun 5, 2026 | ||
| Media design decomposition into RGBA layers | Crello (test) | 32 | May 29, 2026 |