Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 779 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Mathematical Reasoning | AMC 23 | 32 | May 7, 2026 | ||
| Recommendation | Yelp | 32 | Mar 31, 2026 | ||
| Personalized Recommendation | AesRec | 32 | Feb 26, 2026 | ||
| Temporal Autonomous Driving Understanding | TAD 1.0 (test) | 32 | Feb 26, 2026 | ||
| Scene Graph Detection (SGDET) | Action Genome v1.0 (test) | 32 | Feb 26, 2026 | ||
| Visual Question Answering | AnimalKB 1.0 (test) | 32 | Feb 26, 2026 | ||
| Document Parsing | OmniDocBench | 32 | May 4, 2026 | ||
| Pose Estimation | ScanNet++ | 32 | Jul 2, 2026 | ||
| Visual Question Answering | CLEAR 1.0 (Retain) | 32 | Feb 26, 2026 | ||
| Gene expression prediction | Kidney | 32 | May 15, 2026 | ||
| Gene expression prediction | HER2 | 32 | May 15, 2026 | ||
| Gene expression prediction | Breast Cancer | 32 | May 15, 2026 | ||
| Emotion Classification | FI | 32 | Apr 15, 2026 | ||
| Novel View Synthesis | DTU 10% (test) | 32 | Feb 26, 2026 | ||
| Class-to-image generation | ImageNet | 32 | May 21, 2026 | ||
| Semantic Segmentation | ISPRS Potsdam | 32 | May 19, 2026 | ||
| Image Compression | DIV8K (Evaluation) | 32 | Feb 26, 2026 | ||
| Construction Year Estimation | YearGuessr 1.0 (test) | 32 | Feb 26, 2026 | ||
| text-to-motion generation | HumanML3D 1 (test) | 32 | Feb 26, 2026 | ||
| Semantic Segmentation | WHDLD (test) | 32 | Feb 26, 2026 | ||
| Response Classification | Aegis Text Response 2.0 | 32 | Mar 4, 2026 | ||
| Glaucoma Detection | LAG (test) | 32 | Feb 26, 2026 | ||
| Vision-language grounding | MS-COCO 2014 (val) | 32 | Feb 26, 2026 | ||
| subject-to-video generation | OpenS2V | 32 | Jun 9, 2026 | ||
| Autonomous Driving | Bench2Drive base set closed-loop | 32 | May 15, 2026 |