Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1735 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Graph Classification | Molbace scaffold split | 19 | May 4, 2026 | ||
| Class Incremental Learning | DomainNet | 19 | May 28, 2026 | ||
| Natural Language Understanding | LM Evaluation Harness | 19 | Feb 26, 2026 | ||
| Anomaly Detection | Anomaly Detection Challenge Zero-Shot blind (test) | 19 | Mar 11, 2026 | ||
| Accident prediction | Iowa (test) | 19 | Feb 26, 2026 | ||
| Accident prediction | Montana (test) | 19 | Feb 26, 2026 | ||
| Accident prediction | Nevada (test) | 19 | Feb 26, 2026 | ||
| Accident prediction | Maryland (test) | 19 | Feb 26, 2026 | ||
| Accident prediction | Massachusetts (test) | 19 | Feb 26, 2026 | ||
| Accident prediction | Delaware (test) | 19 | Feb 26, 2026 | ||
| Mathematical Problem Solving | OlympiadBench (test) | 19 | Jun 30, 2026 | ||
| Locomotion | NeoRL Walker2d Medium | 19 | Mar 10, 2026 | ||
| Locomotion | NeoRL HalfCheetah-Medium | 19 | Mar 10, 2026 | ||
| Locomotion | NeoRL Walker2d Low | 19 | Mar 10, 2026 | ||
| Locomotion | NeoRL Hopper-Low | 19 | Mar 10, 2026 | ||
| Node Classification | MAG CN -> US (test) | 19 | May 12, 2026 | ||
| Node Classification | MAG US -> DE (test) | 19 | May 12, 2026 | ||
| Node Classification | MAG US -> CN (test) | 19 | May 12, 2026 | ||
| Classification | MEPS | 19 | Feb 26, 2026 | ||
| Classification | LSAC | 19 | Feb 26, 2026 | ||
| Offline Reinforcement Learning | puzzle-3x3-play OGBench 5 tasks v0 | 19 | Mar 4, 2026 | ||
| Offline Reinforcement Learning | cube-double-play OGBench 5 tasks v0 | 19 | Mar 4, 2026 | ||
| Optimization | Rosenbrock function | 19 | Jun 5, 2026 | ||
| Counterfactual Explanation Generation | diggle table a1 | 19 | May 29, 2026 | ||
| Model Reconstruction | HELOC | 19 | Jun 29, 2026 |