Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 2032 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Recommendation | FilmTrust | 17 | Apr 20, 2026 | ||
| Tool-calling | BFCL | 17 | Mar 13, 2026 | ||
| Semantic Type Annotation | SOTAB sch-s | 17 | Apr 23, 2026 | ||
| Video Question Answering | MLVU MCQ | 17 | Mar 13, 2026 | ||
| News Summarization | Multi-News | 17 | Jun 4, 2026 | ||
| Class Incremental Learning | CUB200 Inc10 (test) | 17 | Mar 24, 2026 | ||
| EEG Classification | ERN (test) | 17 | Mar 12, 2026 | ||
| EEG Classification | SSVEP (test) | 17 | Mar 12, 2026 | ||
| EEG Classification | MI (test) | 17 | Mar 12, 2026 | ||
| Image Dehazing | RTTS, URHI, and Fattal | 17 | Mar 12, 2026 | ||
| Image Dehazing | Fattal | 17 | Mar 12, 2026 | ||
| Image Dehazing | URHI | 17 | Mar 12, 2026 | ||
| Multi-talker Automatic Speech Recognition | Libri3Mix Clean (dev) | 17 | Mar 31, 2026 | ||
| Multi-talker Automatic Speech Recognition | Libri3Mix Noisy (dev) | 17 | Mar 31, 2026 | ||
| Multi-talker Automatic Speech Recognition | Libri2Mix Noisy (dev) | 17 | Mar 31, 2026 | ||
| Depth Completion | Overall Average (ScanNet, IBims-1, VOID, NYUv2, KITTI, DDAD) | 17 | Mar 12, 2026 | ||
| Question Answering | MedQA | 17 | Mar 12, 2026 | ||
| Code Generation | MBPP | 17 | Apr 9, 2026 | ||
| Question Answering | SciQ | 17 | Jun 8, 2026 | ||
| Depth Estimation | Heidelberg Light Field Benchmark | 17 | Mar 12, 2026 | ||
| Oriented Object Detection | FAIR-1M 2.0 | 17 | Mar 11, 2026 | ||
| Graph Anomaly Detection | Elliptic (test) | 17 | Mar 11, 2026 | ||
| Anomaly Detection | elliptic zero-shot (test) | 17 | Mar 11, 2026 | ||
| Anomaly Detection | T-Finance zero-shot (test) | 17 | Mar 11, 2026 | ||
| Retrieval | LongMemEval-S | 17 | Apr 6, 2026 |