Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1786 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Visual Grounding | Out-of-Distribution OOD Avg (test) | 18 | Jul 3, 2026 | ||
| Visual Grounding | Out-of-Distribution Scatter Plot (test) | 18 | Jul 3, 2026 | ||
| Visual Grounding | Out-of-Distribution Bar Chart (test) | 18 | Jul 3, 2026 | ||
| Visual Grounding | Cell Query Out-of-Distribution (test) | 18 | Jul 3, 2026 | ||
| Visual Grounding | Out-of-Distribution Large Table (test) | 18 | Jul 3, 2026 | ||
| Visual Grounding | In-Distribution (test) | 18 | Jul 3, 2026 | ||
| Image Generation | ImageNet 256 (val) | 18 | Jul 3, 2026 | ||
| Linear Regression In-context Learning | Garg Linear Regression (d=20) | 18 | Jul 3, 2026 | ||
| Alzheimer's Disease Diagnosis | ADNI Class Balanced (test) | 18 | Jul 3, 2026 | ||
| Professional Fitness Certification Exam | NSCA-CSCS | 18 | Jul 3, 2026 | ||
| Professional Fitness Certification Exam | ACSM-EP | 18 | Jul 3, 2026 | ||
| General Competency Assessment | General-Bench | 18 | Jul 3, 2026 | ||
| Multi-view Depth Estimation | Bonn | 18 | Jul 3, 2026 | ||
| Document Visual Question Answering | DocVQA | 18 | Jul 3, 2026 | ||
| Jailbreaking | AdvBench 520 | 18 | Jul 3, 2026 | ||
| Jailbreaking | HarmBench n = 200 | 18 | Jul 3, 2026 | ||
| Jailbreaking | JBB n = 100 | 18 | Jul 3, 2026 | ||
| Packet Loss Concealment | MAESTRO Solo Piano 50-minute file (single file per loss rate) | 18 | Jul 3, 2026 | ||
| Dynamic Scene Reconstruction | Neu3D (all scenes) | 18 | Jul 3, 2026 | ||
| Few-shot classification | FSC-89 to NSynth-100 | 18 | Jul 3, 2026 | ||
| Few-shot Open-set Audio Classification | Domestic Environments | 18 | Jul 3, 2026 | ||
| Remote Sensing Visual Grounding | DIOR-RSVG | 18 | Jul 2, 2026 | ||
| 3D Medical Image Segmentation | OAI-ZIB (test) | 18 | Jul 2, 2026 | ||
| Quadruped Locomotion Robustness | Mixed Velocity Quadruped Locomotion (Evaluation Rollouts) | 18 | Jul 2, 2026 | ||
| Structured Occlusion Reasoning | nuScenes PKL-guided v1.0 (val) | 18 | Jul 2, 2026 |