Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 501 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| CBCT Reconstruction | AAPM Clinical Dataset 40-view | 42 | May 1, 2026 | ||
| CBCT Reconstruction | AAPM Clinical Dataset 20-view | 42 | May 1, 2026 | ||
| Safety Refusal | Refusal | 42 | Apr 28, 2026 | ||
| Negative Sentiment Generation | Negsentiment | 42 | Apr 28, 2026 | ||
| Refusal | Llama-3-8B n≈200 | 42 | Apr 28, 2026 | ||
| Negative Sentiment | Llama-3-8B n≈200 | 42 | Apr 28, 2026 | ||
| Refusal Backdoor Detection | Gemma-2-9B | 42 | Apr 28, 2026 | ||
| Counterfactual Prediction | Synthetic Dataset | 42 | Apr 28, 2026 | ||
| Counterfactual Prediction | Synthetic Dataset (test) | 42 | Apr 28, 2026 | ||
| Counterfactual Prediction | Synthetic Dataset | 42 | Apr 28, 2026 | ||
| Audio Understanding | MMAU Pro | 42 | Jun 2, 2026 | ||
| Pedagogical Tutoring | SHAPE | 42 | Apr 27, 2026 | ||
| Travel planning | TravelPlanner (val) | 42 | Jun 9, 2026 | ||
| Video-to-Text Retrieval | MSRVTT 1kA severity degree 2 | 42 | Apr 24, 2026 | ||
| Cooperative Decision-Making | Mixed-traffic Unsignalized Intersection Simulation (test) | 42 | Apr 23, 2026 | ||
| Semantic Segmentation | Pascal VOC without background 2012 V20 | 42 | Apr 29, 2026 | ||
| Vulnerability Detection | BigVul | 42 | Apr 30, 2026 | ||
| Safety Detection | Alpaca + XSTest full (val-selected) | 42 | Apr 23, 2026 | ||
| Refusal Detection | Alpaca + XSTest (val) | 42 | Apr 23, 2026 | ||
| Semantic Segmentation (Cropland) | AI4SmallFarms | 42 | Apr 23, 2026 | ||
| Semantic Segmentation (Burn Scars) | AI4SmallFarms | 42 | Apr 23, 2026 | ||
| Reasoning | WebInstruct | 42 | Apr 21, 2026 | ||
| Image Classification | CIFAR10-C | 42 | Apr 21, 2026 | ||
| Multiclass Classification | OpenML 11 multiclass (test) | 42 | Apr 21, 2026 | ||
| Binary Classification | 11 binary datasets OpenML (test) | 42 | Apr 21, 2026 |