Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 634 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Relighting | Forest Environment | 36 | May 1, 2026 | ||
| Relighting | Fireplace Environment | 36 | May 1, 2026 | ||
| Classification | Image Segmentation UCI ML repository (test) | 36 | Apr 30, 2026 | ||
| Classification | Letter recognition UCI (test) | 36 | Apr 30, 2026 | ||
| Audio Deepfake Detection | ASVspoof LA 2019 (eval) | 36 | Jul 1, 2026 | ||
| OOD Detection | SSB Hard | 36 | May 11, 2026 | ||
| Science Question Answering | SQA | 36 | Jun 5, 2026 | ||
| Recommendation | Amazon Toys | 36 | Apr 29, 2026 | ||
| Recommendation | Amazon Health | 36 | Apr 29, 2026 | ||
| Visual Counting | CountBench | 36 | May 29, 2026 | ||
| Speculative Advice Induction | SecLens Multimodal (test) | 36 | Apr 28, 2026 | ||
| Excessive Response Induction | SecLens Multimodal (test) | 36 | Apr 28, 2026 | ||
| Out-of-Distribution Detection | ImageNet (ID) vs SSB-hard OOD (test) | 36 | May 15, 2026 | ||
| Model Merging | Large-scale tasks | 36 | Apr 28, 2026 | ||
| Image Classification | Evaluation suite OOD | 36 | Apr 28, 2026 | ||
| Image Classification | Evaluation suite (ID) | 36 | Apr 28, 2026 | ||
| Image Classification | CIFAR-10-LTN | 36 | Apr 28, 2026 | ||
| Pruning | Pythia 1B (16L), 410M (24L) (val) | 36 | Apr 28, 2026 | ||
| Iris Verification | ImmerIris Right 1.0 | 36 | Apr 28, 2026 | ||
| Iris Verification | ImmerIris 1.0 (Left) | 36 | Apr 28, 2026 | ||
| Watermark Removal | ImageNet (test) | 36 | Apr 27, 2026 | ||
| Daily Irradiance Forecasting | Solaris Real Experiments Location 2 | 36 | Apr 27, 2026 | ||
| Instruction following and safety evaluation | Alpaca | 36 | Apr 24, 2026 | ||
| Graph Reconstruction | PubMed | 36 | May 6, 2026 | ||
| Image Classification | CIFAR-10 | 36 | Apr 23, 2026 |