Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1884 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Temperature at 850hPa (T850) Ensemble Forecasting | ERA5 | 18 | Mar 6, 2026 | ||
| 2m Temperature (T2m) Ensemble Forecasting | ERA5 | 18 | Mar 6, 2026 | ||
| Image Super-resolution | CelebA 19,962 (test) | 18 | Mar 5, 2026 | ||
| 3D Object Classification | ModelNet40 26 (test) | 18 | Mar 5, 2026 | ||
| Image Classification | CCC | 18 | Jun 19, 2026 | ||
| HER2 status classification | TCGA BRCA | 18 | Apr 20, 2026 | ||
| Instruction Following | UltraFeed | 18 | May 7, 2026 | ||
| Speech separation | WHAM! 2-speaker (test) | 18 | Mar 5, 2026 | ||
| Video depth estimation | Unreal4K | 18 | Mar 5, 2026 | ||
| Video depth estimation | UrbanSyn | 18 | Mar 5, 2026 | ||
| Video depth estimation | Monkaa | 18 | Mar 5, 2026 | ||
| Video depth estimation | GMU | 18 | Mar 5, 2026 | ||
| Node Classification | PubMed Planetoid public | 18 | Mar 18, 2026 | ||
| Common and General Video Commentary | Ego4d | 18 | Mar 5, 2026 | ||
| Intent Understanding | Weibo Post-Sync | 18 | Mar 5, 2026 | ||
| Reward-hacking detection | School of Reward Hacks and Stanford Alpaca (test) | 18 | Mar 5, 2026 | ||
| PDE solving | Shallow Water 3D (test) | 18 | Mar 4, 2026 | ||
| PDE solving | Kuramoto-Sivashinsky 1D (test) | 18 | Mar 4, 2026 | ||
| Flexible Job Shop Scheduling | mk Brandimarte | 18 | Mar 4, 2026 | ||
| Planning | HM3D | 18 | Mar 4, 2026 | ||
| Searching | HM3D | 18 | Mar 4, 2026 | ||
| Classification | Resisc45 | 18 | Apr 21, 2026 | ||
| State Estimation | TII-RATM Autonomous 1.0 | 18 | Mar 4, 2026 | ||
| GPU kernel code generation and optimization | KernelBench Level 3 (test) | 18 | Mar 4, 2026 | ||
| GPU kernel code generation and optimization | KernelBench Level 2 (test) | 18 | Mar 4, 2026 |