Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 950 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Automatic Speech Recognition | LibriSpeech other Speech Noise - Reverb (test) | 28 | Mar 16, 2026 | ||
| Automatic Speech Recognition | LibriSpeech clean Speech Noise - Reverb (test) | 28 | Mar 16, 2026 | ||
| Automatic Speech Recognition | LibriSpeech other Speech Noise - Additive (test) | 28 | Mar 16, 2026 | ||
| Automatic Speech Recognition | LibriSpeech clean Speech Noise - Additive (test) | 28 | Mar 16, 2026 | ||
| Medical Question Answering | MMLU-Pro Health | 28 | Jul 3, 2026 | ||
| Text Adversarial Example Detection | Yelp | 28 | Mar 16, 2026 | ||
| Text Adversarial Example Detection | IMDB | 28 | Mar 16, 2026 | ||
| Text Adversarial Example Detection | Ag-News | 28 | Mar 16, 2026 | ||
| Scientific Reasoning | GPQA | 28 | Apr 10, 2026 | ||
| Graph Classification | GOOD-SST2 length | 28 | Apr 10, 2026 | ||
| Seizure Frequency Extraction | Real 300 Pragmatic 1.0 | 28 | Mar 13, 2026 | ||
| Object-Centric Representation Learning | VOC | 28 | Mar 13, 2026 | ||
| Classification | ADNI CN vs AD (test) | 28 | Jun 19, 2026 | ||
| Continual Learning | CIFAR-100 (10-task split) | 28 | Jul 7, 2026 | ||
| OOD Detection | CIFAR10 | 28 | Apr 14, 2026 | ||
| Agentic Multimodal Tool-use | RealX-Bench | 28 | Mar 12, 2026 | ||
| Node Classification | Goodreads-NC (test) | 28 | Mar 11, 2026 | ||
| Node Classification | Ele-Fashion (test) | 28 | Mar 11, 2026 | ||
| Graph classification | obgn-arXiv (test) | 28 | May 22, 2026 | ||
| Image Classification | CIFAR (test) | 28 | May 22, 2026 | ||
| Cross-modal geo-localization | CORE Intercontinental-level Subset3 1.0 | 28 | Jun 23, 2026 | ||
| Cross-modal geo-localization | CORE Intercontinental-level Subset1 1.0 | 28 | Jun 23, 2026 | ||
| Cross-modal Geo-localization | CVG-Text (Brisbane) | 28 | Jun 23, 2026 | ||
| Music Genre Classification | FMA (Free Music Archive) | 28 | Jun 26, 2026 | ||
| Speaker Identification | VoxCeleb 1 | 28 | Jun 26, 2026 |