Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 455 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Graph Classification | DD D0 → D2 (target) | 45 | Jun 2, 2026 | ||
| Multi-Document Question Answering | LongBench | 45 | May 19, 2026 | ||
| Reinforcement Learning | Walker2D v5 | 45 | Apr 3, 2026 | ||
| Adversarial Transfer Attack | Traffic | 45 | Feb 26, 2026 | ||
| Adversarial Transfer Attack | ECL | 45 | Feb 26, 2026 | ||
| Adversarial Transfer Attack | ETT | 45 | Feb 26, 2026 | ||
| Video Question Answering | VideoMME 16 (test) | 45 | Feb 26, 2026 | ||
| Video Question Answering | LongVideoBench (LVB) 58 (test) | 45 | Feb 26, 2026 | ||
| Video Question Answering | MLVU 78 (test) | 45 | Feb 26, 2026 | ||
| Video Understanding | VideoMME (test) | 45 | Apr 21, 2026 | ||
| Grounded Video Question Answering | NExT-GQA (test) | 45 | Jul 7, 2026 | ||
| 2D Medical Image Segmentation | FIVES | 45 | Jul 2, 2026 | ||
| Object Hallucination | POPE Adversarial v1.0 | 45 | Apr 28, 2026 | ||
| Portrait Privacy Protection | SyncTalk-generated videos (test) | 45 | Feb 26, 2026 | ||
| Vision-Language Navigation | OpenUAV unseen hard 1.0 (test) | 45 | Jul 1, 2026 | ||
| Vision-Language Navigation | OpenUAV unseen easy 1.0 (test) | 45 | Jul 1, 2026 | ||
| Few-Shot Class-Incremental Learning | MiniImageNet | 45 | May 12, 2026 | ||
| Counting | CountBenchQA | 45 | May 12, 2026 | ||
| Text-to-Image Generation | Imagine-Bench | 45 | May 15, 2026 | ||
| Enhancing Tumor Segmentation | Pretreat-MetsToBrain-Masks | 45 | Jun 9, 2026 | ||
| Tumor Core Segmentation | Pretreat-MetsToBrain-Masks | 45 | Jun 9, 2026 | ||
| Visual Document Retrieval | ViDoRe Avg. across 4 datasets v2 | 45 | Mar 16, 2026 | ||
| Multimodal Sarcasm Detection | MMSD 2.0 (test) | 45 | Apr 9, 2026 | ||
| Temporal forgery localization | LAV-DF | 45 | Jul 7, 2026 | ||
| Visual Question Answering | V* | 45 | Apr 15, 2026 |