Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1136 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Question Answering | SciDQA | 25 | Feb 26, 2026 | ||
| Class-incremental learning | CIFAR-100 T=20 (test) | 25 | Mar 12, 2026 | ||
| Question Generation | EduMath-CQ | 25 | Feb 26, 2026 | ||
| Tool Calling | API-Bank L-2 | 25 | Feb 26, 2026 | ||
| Text-to-3D | Toys4k | 25 | May 29, 2026 | ||
| Phone Feature Recognition | Buckeye (sociophonetic) | 25 | Feb 26, 2026 | ||
| Mathematical Reasoning | ASDiv Aug (test) | 25 | Feb 26, 2026 | ||
| Fact-checking | ExpertQA | 25 | May 12, 2026 | ||
| Autonomous Driving | Bench2Drive Multi-Ability | 25 | May 15, 2026 | ||
| Class-conditional Image Synthesis | ImageNet | 25 | Feb 26, 2026 | ||
| Counter-Perception Discrimination | CP-Bench (dev) | 25 | Feb 26, 2026 | ||
| Counter-Perception Discrimination | CP-Bench (test) | 25 | Feb 26, 2026 | ||
| Multi-Object Tracking | BEE24 (test) | 25 | Apr 30, 2026 | ||
| Camera Pose Estimation | Co3D Bench, Skateboard, Plant, Hydrant, Teddy | 25 | Feb 26, 2026 | ||
| Stereo Matching | KITTI 2015 (non-occluded) | 25 | Feb 26, 2026 | ||
| Temporal Grounding | Ego4D-NLQ | 25 | Apr 10, 2026 | ||
| Class-incremental learning | CIFAR-10 (test) | 25 | Feb 26, 2026 | ||
| Image Deraining | Rain within-distribution Standard | 25 | Feb 26, 2026 | ||
| Classification | Flowers | 25 | May 14, 2026 | ||
| Character Consistency | CharacterEval | 25 | Mar 4, 2026 | ||
| 3D Semantic Segmentation | ScanNet200 (val) | 25 | Jul 2, 2026 | ||
| Base-to-novel Image Classification | FGVC Aircraft | 25 | May 18, 2026 | ||
| Infrared and visible image fusion | M3FD | 25 | May 14, 2026 | ||
| Video Person Re-identification | G2A-VReID Ground to Aerial | 25 | Feb 26, 2026 | ||
| Anomaly Detection | MPDD | 25 | Jul 3, 2026 |