Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 2066 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Image Classification | STL-10 250 labels | 17 | Feb 26, 2026 | ||
| Text Classification | 20 Newsgroups Dir(0.01) (test) | 17 | Feb 26, 2026 | ||
| Text Classification | 20 Newsgroups Dir(0.1) (test) | 17 | Feb 26, 2026 | ||
| Text Classification | 20 Newsgroups Dir(0.5) (test) | 17 | Feb 26, 2026 | ||
| Text Classification | BANKING77 Dir(0.1) (test) | 17 | Feb 26, 2026 | ||
| Text Classification | BANKING77 Dir(0.5) (test) | 17 | Feb 26, 2026 | ||
| Compressive Sensing Image Reconstruction | Set11 (test) | 17 | Feb 26, 2026 | ||
| Phone Feature Recognition | L2-Perceived sociophonetic | 17 | Feb 26, 2026 | ||
| Phone Feature Recognition | L2-Standard (sociophonetic) | 17 | Feb 26, 2026 | ||
| Phone Feature Recognition | VoxAngeles unseen languages | 17 | Feb 26, 2026 | ||
| Phone Feature Recognition | Doreco (unseen languages) | 17 | Feb 26, 2026 | ||
| Machine Translation | Seen Dataset en-te 1.0 | 17 | Feb 26, 2026 | ||
| Machine Translation | Seen Dataset en-ta 1.0 | 17 | Feb 26, 2026 | ||
| Machine Translation | Seen Dataset en-bn 1.0 | 17 | Feb 26, 2026 | ||
| Machine Translation | Seen Dataset en-hi 1.0 | 17 | Feb 26, 2026 | ||
| Text Generation | CommonGen | 17 | Jun 17, 2026 | ||
| Word Segmentation | MSR Chinese (test) | 17 | Feb 26, 2026 | ||
| Code Generation | MBPP extended (test) | 17 | Feb 26, 2026 | ||
| Video Virtual Try-On | ViViD (test) | 17 | Jun 25, 2026 | ||
| Multi-modal Question Answering | MMStar (test) | 17 | Apr 28, 2026 | ||
| Multi-modal Question Answering | MMMU (val) | 17 | May 6, 2026 | ||
| Text-to-Speech | LibriSpeech clean PC (test) | 17 | Feb 26, 2026 | ||
| Temporal Reasoning Prediction | WIKI (test) | 17 | Feb 26, 2026 | ||
| Temporal Reasoning Prediction | ICEWS18 (test) | 17 | Feb 26, 2026 | ||
| Explanation Generation | ICEWS05-15 (test) | 17 | Feb 26, 2026 |