Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 2731 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Zero-shot Retrieval (T → A+V) | VALOR | 14 | Feb 27, 2026 | ||
| Video-to-Text Retrieval | Kinetics-700 | 14 | Feb 27, 2026 | ||
| Video-to-Text Retrieval | Kinetics-600 | 14 | Feb 27, 2026 | ||
| Video-to-Text Retrieval | Kinetics-400 | 14 | Feb 27, 2026 | ||
| LTL Instruction Following | Zones Infinite-horizon (full) | 14 | Feb 27, 2026 | ||
| Tracking | RPNG AR Table Dataset Stride 20 | 14 | Feb 27, 2026 | ||
| Agentic Search | MuSiQue | 14 | Apr 7, 2026 | ||
| Prompt Classification | XSTest Text Prompt | 14 | Feb 27, 2026 | ||
| Prompt Classification | WildGuard Text Prompt | 14 | Feb 27, 2026 | ||
| Prompt Classification | ToxicChat Text Prompt | 14 | Feb 27, 2026 | ||
| Prompt Classification | Simple SafetyTest Text Prompt | 14 | Feb 27, 2026 | ||
| Prompt Classification | OpenAI Moderation Text Prompt | 14 | Feb 27, 2026 | ||
| Prompt Classification | Aegis Text Prompt 2.0 | 14 | Feb 27, 2026 | ||
| Latency Analysis | LVLM generation | 14 | Feb 27, 2026 | ||
| Point Cloud Purification | ShapeNet | 14 | Feb 27, 2026 | ||
| Point Cloud Purification | ModelNet40 | 14 | Feb 27, 2026 | ||
| Point Cloud Matching | SHREC07-H | 14 | Feb 27, 2026 | ||
| Point Cloud Matching | SHREC'19_r | 14 | Feb 27, 2026 | ||
| Base-to-new class generalization | ShapeNetCore V2 (test) | 14 | Jun 18, 2026 | ||
| Base-to-new class generalization | ScanObjectNN S-OBJ_ONLY (test) | 14 | Jun 18, 2026 | ||
| Base-to-new class generalization | ScanObjectNN S-PB_T50_RS (test) | 14 | Jun 18, 2026 | ||
| Text-to-Image Retrieval | QUILT-1M (holdout set) | 14 | Feb 27, 2026 | ||
| Meta-continual learning | CIFAR100 10/10 | 14 | Feb 27, 2026 | ||
| Mathematical Reasoning | MATH | 14 | Feb 27, 2026 | ||
| Audio-visual Recognition | VGGSound GZSL | 14 | Feb 27, 2026 |