Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 905 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Multitask Language Understanding | MMLU CoT | 29 | Mar 4, 2026 | ||
| Synthetic Grammar Synthesis | Synthetic Grammar Synthesis a^n b^n c^n | 29 | Apr 14, 2026 | ||
| Target-Aspect-Sentiment Detection | Hotels | 29 | May 28, 2026 | ||
| Target-Aspect-Sentiment Detection | Coursera | 29 | May 28, 2026 | ||
| Few-Shot Class-Incremental Learning | CUB200 Session 10 - Last (test) | 29 | Mar 4, 2026 | ||
| Few-Shot Class-Incremental Learning | CUB200 Session 2 (test) | 29 | Mar 4, 2026 | ||
| Phase retrieval | ImageNet | 29 | May 19, 2026 | ||
| General Capability | All Benchmarks Overall | 29 | Apr 14, 2026 | ||
| Code Generation | LCB | 29 | Jun 30, 2026 | ||
| Grounding | ScreenSpot v2 (test) | 29 | Apr 16, 2026 | ||
| n-body particle system sampling | DW-4 d = 8 | 29 | May 20, 2026 | ||
| General Multimodal Understanding | BLINK | 29 | Jun 30, 2026 | ||
| Boolean Question Answering | BoolQ | 29 | Apr 9, 2026 | ||
| Multi-turn Image Editing | MSE-Bench | 29 | Jun 11, 2026 | ||
| GUI Localization | GUIZoom-Bench hard-est | 29 | Feb 27, 2026 | ||
| GUI Localization | GUIZoom-Bench hard-mislead | 29 | Feb 27, 2026 | ||
| GUI Localization | GUIZoom-Bench easy-mislead | 29 | Feb 27, 2026 | ||
| GUI Localization | GUIZoom-Bench easy-normal | 29 | Feb 27, 2026 | ||
| Volume Estimation | MetaFood3D | 29 | Apr 14, 2026 | ||
| Synthetic in-context reasoning | MAD synthetic (test) | 29 | May 29, 2026 | ||
| Multi-modal Understanding | SEED-IMG | 29 | Apr 27, 2026 | ||
| Capacitated Vehicle Routing Problem | CVRP 1000 | 29 | May 26, 2026 | ||
| OOD Detection | Places365 OOD (test) | 29 | Mar 26, 2026 | ||
| Visual Question Answering | VQA^T | 29 | Apr 24, 2026 | ||
| Summarization | eBay Email | 29 | Feb 26, 2026 |