Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1297 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Software Engineering | SWE-bench Verified | 23 | Jul 7, 2026 | ||
| 3D Occupancy Prediction | SurroundOcc | 23 | Jun 23, 2026 | ||
| UI Polishing | UIPolish-Synthetic | 23 | May 7, 2026 | ||
| UI Polishing | UIPolish Real | 23 | May 7, 2026 | ||
| UI Drafting | UI2Code-Real | 23 | May 7, 2026 | ||
| UI Drafting | Web2Code | 23 | May 7, 2026 | ||
| UI Drafting | Flame | 23 | May 7, 2026 | ||
| UI Drafting | Design2Code | 23 | May 7, 2026 | ||
| Discriminative Hallucination Evaluation | AMBER-d | 23 | Jun 1, 2026 | ||
| Zero-shot Evaluation | MobileLLM Evaluation Suite zero-shot | 23 | May 7, 2026 | ||
| Visual Question Answering | INFOSEEK Unseen-E | 23 | May 6, 2026 | ||
| Visual Question Answering | E-VQA All | 23 | May 6, 2026 | ||
| Engagement classification | DAiSEE | 23 | May 6, 2026 | ||
| Multi-modal Toxicity Attack | PTP (PolygloToxicityPrompts) English (test) | 23 | May 4, 2026 | ||
| AI-generated video detection | GenVideo (test) | 23 | May 8, 2026 | ||
| Fine-Grained Classification | FGVC-Aircraft (test) | 23 | Jun 30, 2026 | ||
| Image Classification | SVHN (test) | 23 | Jun 5, 2026 | ||
| Semantic Segmentation | Pascal Context Stuff without background | 23 | Apr 29, 2026 | ||
| Semantic Segmentation | COCO-60 with background | 23 | Apr 29, 2026 | ||
| Long-Context Retrieval | RULER 128K | 23 | Jul 7, 2026 | ||
| Grounding | RefCOCO (val) | 23 | Jul 8, 2026 | ||
| Mathematics Competition | AIME 25 | 23 | Jun 26, 2026 | ||
| Machine Translation | WMT EN→ZH 23 | 23 | Apr 28, 2026 | ||
| Change Captioning | WHU-CDC | 23 | May 7, 2026 | ||
| PDF-to-LaTeX reconstruction | TEXOCR-Bench 1.0 (test) | 23 | Apr 28, 2026 |