Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1363 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Orientation estimation | T-LESS SiSo | 22 | Apr 21, 2026 | ||
| Privacy-preserving dialogue processing | Med-PCD (test) | 22 | Apr 21, 2026 | ||
| Privacy-preserving dialogue processing | PUPA-TNB (test) | 22 | Apr 21, 2026 | ||
| Attacker Detection | Qwen3-1.7B target τpool=1.509 (test) | 22 | Apr 21, 2026 | ||
| Differential Morphing Attack Detection | FERET to FRGC cross-database | 22 | Apr 21, 2026 | ||
| Interactive Environment Task Completion | WebShop (Seen) | 22 | Apr 21, 2026 | ||
| Interactive Environment Task Completion | ScienceWorld (Seen) | 22 | Apr 21, 2026 | ||
| Scientific Reasoning | GPQA-D | 22 | Apr 21, 2026 | ||
| Mathematical Reasoning | AIME 2025 | 22 | Apr 21, 2026 | ||
| Mathematical Reasoning | MATH500 | 22 | Apr 21, 2026 | ||
| Free-form text generation | CoQA | 22 | Jun 2, 2026 | ||
| Scene Graph Detection (SGDET) | Action Genome (test) | 22 | Apr 23, 2026 | ||
| Handwritten Text Recognition | IAM-5 | 22 | Apr 21, 2026 | ||
| Handwriting Recognition | IAM-5-Random | 22 | Apr 21, 2026 | ||
| Depression Assessment | DAIC-WOZ | 22 | May 22, 2026 | ||
| Question Answering | ARC Challenge | 22 | May 11, 2026 | ||
| Chemical property prediction | 11 Engineering Datasets | 22 | Apr 20, 2026 | ||
| Machine Unlearning | ToFU NEK | 22 | Apr 20, 2026 | ||
| Multi-View Stereo Reconstruction | Strecha HerzJesu | 22 | Apr 20, 2026 | ||
| Multi-View Stereo Reconstruction | Strecha Fountain | 22 | Apr 20, 2026 | ||
| GUI Understanding | AndroidControl High | 22 | Apr 16, 2026 | ||
| Tool-use Inference | BFCL v2 | 22 | Apr 16, 2026 | ||
| Tool-use Inference | ToolAlpaca | 22 | Apr 16, 2026 | ||
| Tool-use Inference | API-Bank | 22 | Apr 16, 2026 | ||
| Traveling Salesman Problem | TSP50K generated | 22 | Jun 4, 2026 |