Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1422 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Oriented Object Detection | FAIR1M v1.0 | 22 | Jun 5, 2026 | ||
| Scene Classification | UCMerced 82 (80% train 20% test) | 22 | Feb 26, 2026 | ||
| Image Editing | GEdit-Bench-EN v1.0 (Full set) | 22 | Feb 26, 2026 | ||
| Surgical Instrument Segmentation | EndoVis 2017 (test) | 22 | Feb 26, 2026 | ||
| Process Reward Modeling | PRMBENCH | 22 | Apr 21, 2026 | ||
| Text Classification | Reuters | 22 | Feb 26, 2026 | ||
| Meeting Summarization | SamSum | 22 | Feb 26, 2026 | ||
| Decision Making | AlfWorld | 22 | Mar 13, 2026 | ||
| Mobile Agent Evaluation | AndroidControl Low (test) | 22 | Mar 16, 2026 | ||
| Toxicity Classification | Toxigen | 22 | Feb 26, 2026 | ||
| Recommendation | TG-REDIAL (test) | 22 | Feb 26, 2026 | ||
| Object Detection | Clipart, Comic, and Watercolor | 22 | Feb 26, 2026 | ||
| Document Summarization | BookSum | 22 | Feb 26, 2026 | ||
| Biomarker Segmentation | Electron Microscopy (EM) (test) | 22 | Feb 26, 2026 | ||
| Instruction Tuning | Dolly-15K alpha=5.0 | 22 | Feb 26, 2026 | ||
| Instruction Tuning | Dolly-15K alpha=0.5 | 22 | Feb 26, 2026 | ||
| Instruction Tuning | Natural Instructions Meta Non-IID | 22 | Feb 26, 2026 | ||
| Language Modeling | LM Evaluation Harness (LM Eval) (test) | 22 | Feb 26, 2026 | ||
| Open-Vocabulary Segmentation | Pascal VOC | 22 | Jun 23, 2026 | ||
| Novel View Synthesis | Deep Blending official (test) | 22 | Feb 26, 2026 | ||
| Anomaly Detection | DTD Synthetic | 22 | Feb 26, 2026 | ||
| Anomaly Detection | WFDD | 22 | Feb 26, 2026 | ||
| Anomaly Detection | BTAD | 22 | Apr 6, 2026 | ||
| Downstream Task Accuracy | FEVER card (test) | 21 | Jul 9, 2026 | ||
| 3D Face Reconstruction Metric Alignment with Human Judgments | REALY | 21 | Jul 9, 2026 |