Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1834 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Camera Location Estimation | ETH3D | 18 | May 11, 2026 | ||
| Eye Movement Biometric Authentication (RAN task) | GazeBaseVR | 18 | May 11, 2026 | ||
| Eye Movement Biometric Authentication (RAN task) | GazeBase | 18 | May 11, 2026 | ||
| EEG Denoising | CHB-MIT EEG contaminated with EMG (test) | 18 | May 11, 2026 | ||
| EEG Denoising | CHB-MIT EEG contaminated with WGN (test) | 18 | May 11, 2026 | ||
| Single-turn Reasoning | Reasoning Tasks AIME24, AIME25, GPQA | 18 | May 8, 2026 | ||
| Mathematical Reasoning | Mathematical Reasoning Average | 18 | May 8, 2026 | ||
| Mathematical Reasoning | AIME 2025 | 18 | May 8, 2026 | ||
| Mathematical Reasoning | AIME 2024 | 18 | May 8, 2026 | ||
| Instruction Following | IFBench | 18 | May 19, 2026 | ||
| Mathematical Reasoning | BeyondAIME | 18 | May 8, 2026 | ||
| Long-form Factuality | Factory | 18 | May 8, 2026 | ||
| Long-form Factuality | LongFact | 18 | May 8, 2026 | ||
| Long-form Factuality | LongWiki | 18 | May 8, 2026 | ||
| Low-Light Enhancement | LOL v1 | 18 | May 8, 2026 | ||
| All-in-One Image Restoration | AIO-3 Protocol SOTS, Rain100L, BSD68 | 18 | May 8, 2026 | ||
| Traveling Salesman Problem | TSP Barbell-500 | 18 | May 8, 2026 | ||
| Traveling Salesman Problem | TSP Barbell-200 | 18 | May 8, 2026 | ||
| Traveling Salesman Problem | TSP Barbell-100 | 18 | May 8, 2026 | ||
| Traveling Salesman Problem | TSP Diagonal-500 | 18 | May 8, 2026 | ||
| Traveling Salesman Problem | TSP Diagonal-200 | 18 | May 8, 2026 | ||
| Traveling Salesman Problem | TSP Diagonal-100 | 18 | May 8, 2026 | ||
| Traveling Salesman Problem | TSP Clustered-500 | 18 | May 8, 2026 | ||
| Traveling Salesman Problem | TSP Clustered-200 | 18 | May 8, 2026 | ||
| Traveling Salesman Problem | TSP Clustered-100 | 18 | May 8, 2026 |