Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 28 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Word Sense Disambiguation | WiC | 261 | May 29, 2026 | ||
| Question Answering | 2WIKI | 260 | Jul 8, 2026 | ||
| Intent Classification | Banking77 | 260 | Jun 1, 2026 | ||
| Image Classification | ImageNet (val) | 260 | Jun 23, 2026 | ||
| Image Super-Resolution | Manga109 (test) | 260 | Apr 24, 2026 | ||
| Question Answering | SQuAD v1.1 (test) | 260 | Feb 27, 2026 | ||
| Object Hallucination Evaluation | POPE | 259 | Jun 30, 2026 | ||
| Language Modeling | FineWeb (val) | 259 | Jun 30, 2026 | ||
| Mathematical Multimodal Reasoning | MathVerse | 259 | May 27, 2026 | ||
| Commonsense Reasoning | ARC Challenge | 259 | Jun 16, 2026 | ||
| Referring Expression Segmentation | RefCOCO (testB) | 259 | Jun 4, 2026 | ||
| Image Deblurring | RealBlur-J (test) | 259 | Jun 5, 2026 | ||
| Reading Comprehension | BoolQ | 258 | Jun 24, 2026 | ||
| Concept Attribution | iSarcasm | 258 | Feb 26, 2026 | ||
| Question Answering | GPQA | 258 | Feb 26, 2026 | ||
| Visual Question Answering | VQA v2 | 257 | Jul 9, 2026 | ||
| Image Super-Resolution | RealSR | 257 | Jun 30, 2026 | ||
| Image Editing | PIE-Bench | 257 | Jul 3, 2026 | ||
| Action Recognition | Something-Something v1 (val) | 257 | Feb 27, 2026 | ||
| Temporal Action Localization | ActivityNet 1.3 (val) | 257 | Feb 26, 2026 | ||
| RGB-T Tracking | LasHeR (test) | 257 | Mar 24, 2026 | ||
| Video Question Answering | EgoSchema (Full) | 256 | Jun 30, 2026 | ||
| Object Detection | DOTA 1.0 (test) | 256 | Mar 11, 2026 | ||
| Text-to-Video retrieval | LSMDC (test) | 256 | Jun 18, 2026 | ||
| Face Verification | AgeDB-30 | 256 | Jun 11, 2026 |