Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 2201 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| OoD Detection | WORM-Pro | 16 | Apr 1, 2026 | ||
| OoD Detection | WORM-Nem | 16 | Apr 1, 2026 | ||
| OoD Detection | WEED-Hand | 16 | Apr 1, 2026 | ||
| OoD Detection | LIZ-SG | 16 | Apr 1, 2026 | ||
| OoD Detection | LIZ-IG | 16 | Apr 1, 2026 | ||
| Failure Detection | Average | 16 | Apr 1, 2026 | ||
| Failure Detection | LIDC-Tex (test) | 16 | Apr 1, 2026 | ||
| Failure Detection | LIDC-Mal (test) | 16 | Apr 1, 2026 | ||
| Failure Detection | ARC-Nuc (test) | 16 | Apr 1, 2026 | ||
| Failure Detection | ARC-BC (test) | 16 | Apr 1, 2026 | ||
| Facial Expression Recognition | RAF-DB B | 16 | Apr 1, 2026 | ||
| Global Localization | OS_NTU Panoramic | 16 | Apr 1, 2026 | ||
| Global Localization | Mid_NTU FoV-limited | 16 | Apr 1, 2026 | ||
| GUI Agent Robustness Evaluation | Pop-up Perturbation Avg. 1.0 | 16 | Apr 1, 2026 | ||
| Multi-agent Coordination | SMAC 1o10b_vs_1r | 16 | Apr 1, 2026 | ||
| Multi-agent Coordination | TJ slow | 16 | Apr 1, 2026 | ||
| Multi-agent Coordination | LBF 3p-1f | 16 | Apr 1, 2026 | ||
| Video Question Answering | LVBench (val) | 16 | Apr 1, 2026 | ||
| Mesh Reconstruction | Replica office 0 | 16 | Jun 2, 2026 | ||
| Mesh Reconstruction | Replica room 1 | 16 | Jun 2, 2026 | ||
| SDF Reconstruction | Replica office 2 | 16 | Apr 27, 2026 | ||
| Natural Language Video Grounding | TACoS (val) | 16 | Apr 1, 2026 | ||
| Crystal structure generation | MP20 | 16 | Apr 1, 2026 | ||
| Image Editing | Arena Analysis March 26, 2026 (test) | 16 | Mar 31, 2026 | ||
| Image Editing | GEditBench v2 (test) | 16 | Mar 31, 2026 |