Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1947 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Dialogue | Dialogue | 18 | Feb 26, 2026 | ||
| Image Classification | ImageNet 1k (val) | 18 | Feb 26, 2026 | ||
| Multi-object tracking | UAVDT (test) | 18 | Feb 26, 2026 | ||
| 3D Object Recognition | ModelNet40 1k points (test) | 18 | Feb 26, 2026 | ||
| Object Hallucination Evaluation | POPE 28 | 18 | Feb 26, 2026 | ||
| Multimodal Perception Evaluation | MME Perception 16 | 18 | Feb 26, 2026 | ||
| Novel View Synthesis | Nuscenes | 18 | May 19, 2026 | ||
| Direct-answer Visual Question Answering | A-OKVQA | 18 | Feb 26, 2026 | ||
| AI-generated text detection | HC3 (test) | 18 | Feb 26, 2026 | ||
| Object Hallucination Evaluation | MME Existence (test) | 18 | Feb 26, 2026 | ||
| Visual Perception | SEED-Bench Image | 18 | Feb 26, 2026 | ||
| Knowledge Base Question Answering | CWQ | 18 | Feb 26, 2026 | ||
| Dog Whistle Presence Detection | Synthetic-Detection 1.0 (test) | 18 | Feb 26, 2026 | ||
| Entity Localization | VRDU Registration Form (test) | 18 | Feb 27, 2026 | ||
| Remote Sensing Change Detection | SYSU-CD (test) | 18 | Feb 26, 2026 | ||
| Machine Translation | WMT 22 (test) | 18 | Feb 26, 2026 | ||
| Machine Translation | WMT En-Zh 22 (test) | 18 | Feb 26, 2026 | ||
| Disentanglement | ARG0 | 18 | Feb 26, 2026 | ||
| Knowledge Base Question Answering | GrailQA 500-sample (dev) | 18 | Feb 26, 2026 | ||
| Simultaneous Speech Translation | CallHome Spanish-English Es-En (test) | 18 | Feb 26, 2026 | ||
| Code Generation | MBPP subset of 500 (test) | 18 | Feb 26, 2026 | ||
| Long-Term Anticipation | Ego4D LTA v1 (test) | 18 | Feb 26, 2026 | ||
| Adversarial Attack Defense | GCG Individual | 18 | Feb 26, 2026 | ||
| Fashion video synthesis | UBC fashion video dataset (test) | 18 | Apr 1, 2026 | ||
| Instruction Following | Vicuna benchmark | 18 | Feb 26, 2026 |