Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1375 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Node Classification | Wisconsin | 22 | Mar 10, 2026 | ||
| Image Captioning | Flickr8k-EX | 22 | Mar 10, 2026 | ||
| Skin lesion classification | HAM10000 | 22 | Jun 17, 2026 | ||
| Question Answering | Pub | 22 | Mar 10, 2026 | ||
| Image Classification | CIFAR10 (test) | 22 | Mar 10, 2026 | ||
| Visual Explanation | ImageNet | 22 | Mar 9, 2026 | ||
| Localization | Boreas (sequences) | 22 | Mar 9, 2026 | ||
| Behavior Selection | CAA (50 random samples) | 22 | Mar 9, 2026 | ||
| Automated Essay Scoring | IELTS Writing Task 2 | 22 | Mar 9, 2026 | ||
| Object Localization | PascalVOC | 22 | Mar 9, 2026 | ||
| Lifelong Embodied Navigation | LENL (test) | 22 | Mar 9, 2026 | ||
| siRNA perturbation classification | RxRx1 out-of-distribution wilds (test) | 22 | Mar 9, 2026 | ||
| JSON Schema Generation | JSON Schema (test) | 22 | Mar 6, 2026 | ||
| Robotic Manipulation | LLCRM 1.0 (test) | 22 | Mar 6, 2026 | ||
| Function Calling | BFCL Multi-turn | 22 | Mar 6, 2026 | ||
| Function Calling | BFCL Single-turn | 22 | Mar 6, 2026 | ||
| Stateful Agent-User Interaction | tau-Bench Airline | 22 | Mar 6, 2026 | ||
| Sequential Tool Use | RestBench Spotify | 22 | Mar 6, 2026 | ||
| Tool-use API Generalization | ToolBench G3 | 22 | Mar 6, 2026 | ||
| Tool-use API Generalization | ToolBench G2 | 22 | Mar 6, 2026 | ||
| Tool-use API Generalization | ToolBench G1 v1 | 22 | Mar 6, 2026 | ||
| Temporal Forgery Localization | AV-Deepfake1M (test) | 22 | May 25, 2026 | ||
| Motor Imagery Classification | SHU-MI | 22 | Mar 24, 2026 | ||
| Node-level Detection | OWASP Top 10 attack simulation cases (test) | 22 | Mar 6, 2026 | ||
| Video Understanding | VideoRefer-BenchQ | 22 | May 19, 2026 |