Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1058 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Image Quality Assessment Correlation | Tanks and Temples | 26 | Apr 7, 2026 | ||
| Multimodal Image Understanding | MMMU | 26 | May 21, 2026 | ||
| Input Moderation | AEGIS (test) | 26 | Apr 14, 2026 | ||
| Feature Selection Alignment | Expert-labeled disease feature relevance dataset | 26 | Apr 7, 2026 | ||
| Mathematical Reasoning | AIME24 | 26 | May 12, 2026 | ||
| End-to-end generation | ASQA | 26 | Apr 6, 2026 | ||
| End-to-end generation | QAMPARI | 26 | Apr 6, 2026 | ||
| Engagement Recognition | EngageNet | 26 | Jun 9, 2026 | ||
| Recommendation | HRT | 26 | Apr 3, 2026 | ||
| Safety Guardrailing | OR-Bench | 26 | Apr 3, 2026 | ||
| Information Retrieval | TREC DL Hard | 26 | Jun 11, 2026 | ||
| Time Series Anomaly Detection | WADI | 26 | Jun 18, 2026 | ||
| Time Series Anomaly Detection | SWaT | 26 | Jun 18, 2026 | ||
| Feature significance testing | Synthetic classification dataset | 26 | Apr 3, 2026 | ||
| Classification | Overall 13 datasets aggregate | 26 | Apr 3, 2026 | ||
| Classification | fashion | 26 | Apr 3, 2026 | ||
| Classification | fb | 26 | Apr 3, 2026 | ||
| Classification | dota2 | 26 | Apr 3, 2026 | ||
| Classification | magic | 26 | Apr 3, 2026 | ||
| Classification | letRecog | 26 | Apr 3, 2026 | ||
| Classification | c-4 | 26 | Apr 3, 2026 | ||
| Classification | banknote | 26 | Apr 3, 2026 | ||
| Multimodal Retrieval (text query to multimodal content) | M5Product (test) | 26 | Apr 2, 2026 | ||
| Low-light Enhancement | BVI-RLV 40 dynamic scenes | 26 | Apr 2, 2026 | ||
| 3D Object Detection | KITTI-J | 26 | Apr 2, 2026 |