Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1438 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Open-ended generation | CARE-pro | 21 | May 26, 2026 | ||
| Regional knowledge and conversational settings | CARE | 21 | May 26, 2026 | ||
| Camera Control Video Generation | Single-Effect Camera Control Dataset | 21 | May 26, 2026 | ||
| Question Answering | ARC C | 21 | Jun 30, 2026 | ||
| Conformal Prediction | ImageNet (five repeated splits) | 21 | May 26, 2026 | ||
| Calibration | Tabular datasets | 21 | May 26, 2026 | ||
| Mathematical Reasoning | AMC 2023 | 21 | May 26, 2026 | ||
| Mathematical Reasoning | AIME 2024 | 21 | May 26, 2026 | ||
| Safety Controllability | Safety Domains | 21 | May 26, 2026 | ||
| Logical Reasoning | Rule-chaining (test) | 21 | May 26, 2026 | ||
| Constraint Satisfaction | Graph Coloring (test) | 21 | May 26, 2026 | ||
| Constraint Satisfaction | N-Queens N=8 (test) | 21 | May 26, 2026 | ||
| Logical Reasoning | Rule-chaining | 21 | May 26, 2026 | ||
| Combinatorial Search | N-Queens N=8 | 21 | May 26, 2026 | ||
| Mathematics | Minerva Math | 21 | May 26, 2026 | ||
| Software Vulnerability Detection | OSV-Bench 1.0 (test) | 21 | May 26, 2026 | ||
| Code Generation | CodeContests | 21 | May 25, 2026 | ||
| Code Generation | LiveCodeBench | 21 | May 25, 2026 | ||
| Code Generation | LiveBench | 21 | May 25, 2026 | ||
| High-dimensional optimization | MSLR | 21 | May 25, 2026 | ||
| Video Generation | Wan 1.3B (81 frames, 832×480) 2.1 | 21 | Jun 26, 2026 | ||
| Constrained Path Planning | Textualized Gridworld Long targets (test) | 21 | May 25, 2026 | ||
| Constrained Path Planning | Textualized Gridworld Safe targets (test) | 21 | May 25, 2026 | ||
| Constrained Path Planning | Textualized Gridworld Short targets (test) | 21 | May 25, 2026 | ||
| Fair agent decision making | School admission continuous | 21 | May 22, 2026 |