Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1986 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Watermark Detection | C4 Post-translation tr-de | 17 | Jul 1, 2026 | ||
| Watermark Detection | C4 Post-paraphrasing | 17 | Jul 1, 2026 | ||
| Watermark Detection | C4 Unmodified | 17 | Jul 1, 2026 | ||
| Grounding | OSWorld-G-Refine (test) | 17 | Jul 1, 2026 | ||
| Interval prediction | Body fat data (test) | 17 | Jul 1, 2026 | ||
| Embodied task planning | BEHAVIOR-1K B-100 1.0 | 17 | Jul 1, 2026 | ||
| Embodied task planning | BEHAVIOR-1K B-1000 1.0 | 17 | Jul 1, 2026 | ||
| Speech-to-Speech reasoning | Kimi-Audio-Evalkit s2s | 17 | Jul 1, 2026 | ||
| Drug-Drug Interaction Prediction | TWOSIDES S2 | 17 | Jul 1, 2026 | ||
| Drug-Drug Interaction Prediction | DrugBank (S2) | 17 | Jul 1, 2026 | ||
| Facial Expression Recognition | MAFW (5-fold cross-validation) | 17 | Jun 30, 2026 | ||
| Monocular Depth Estimation | Stanford2D3D (unseen) | 17 | Jun 30, 2026 | ||
| Monocular Depth Estimation | Matterport3D (unseen) | 17 | Jun 30, 2026 | ||
| General Multimodal Understanding | ChartQA | 17 | Jun 30, 2026 | ||
| General Multimodal Understanding | MM* | 17 | Jun 30, 2026 | ||
| Multimodal Reasoning | LVista | 17 | Jun 30, 2026 | ||
| Multimodal Reasoning | MVerse | 17 | Jun 30, 2026 | ||
| Multimodal Reasoning | MVision | 17 | Jun 30, 2026 | ||
| Multimodal Perception | V* | 17 | Jun 30, 2026 | ||
| Multimodal Perception | MME-RW | 17 | Jun 30, 2026 | ||
| Semantic Segmentation | WHUOHS w/o domain gap | 17 | Jun 30, 2026 | ||
| Semantic Segmentation | MTS12 N→S | 17 | Jun 30, 2026 | ||
| Autonomous Driving Planning | nuScenes ST-P3 (val) | 17 | Jun 30, 2026 | ||
| College-level Reasoning | MMMU (val) | — | 17 | Jun 30, 2026 | |
| Multimodal Science Reasoning | SQA (val) | — | 17 | Jun 30, 2026 |