Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1167 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Long-video understanding | LongVideoBench | 24 | Jun 11, 2026 | ||
| Rollout Prediction | Cahn-Hilliard 3D | 24 | Jun 11, 2026 | ||
| Rollout Prediction | Swift-Hohenberg 3D (test) | 24 | Jun 11, 2026 | ||
| PDE Rollout | Allen-Cahn 3D | 24 | Jun 11, 2026 | ||
| Label Correction | Yahoo! Answer | 24 | Jun 11, 2026 | ||
| Tabular Classification | Diabetes | 24 | Jun 11, 2026 | ||
| Tabular Classification | Amazon | 24 | Jun 11, 2026 | ||
| Tabular Classification | Adult | 24 | Jun 11, 2026 | ||
| Suturing | Suturing | 24 | Jun 11, 2026 | ||
| Surgical Debridement | Debridement subtask | 24 | Jun 11, 2026 | ||
| Multi-Agent Reinforcement Learning | MAMuJoCo HalfCheetah Extreme Env v2 (various) | 24 | Jun 11, 2026 | ||
| Multi-Agent Reinforcement Learning | MAMuJoCo HalfCheetah Random Env v2 (various) | 24 | Jun 11, 2026 | ||
| Multi-Agent Reinforcement Learning | MAMuJoCo HalfCheetah Standard Env v2 (various) | 24 | Jun 11, 2026 | ||
| Planning | nuPlan (test14) | 24 | Jun 11, 2026 | ||
| Sycophancy Evaluation | MIST Moral | 24 | Jun 11, 2026 | ||
| Sycophancy Evaluation | MIST Science | 24 | Jun 11, 2026 | ||
| Trajectory Classification | Starkey Dataset | 24 | Jun 11, 2026 | ||
| Trajectory Classification | Foxes Dataset | 24 | Jun 11, 2026 | ||
| Trajectory Classification | Car Traffic Dataset | 24 | Jun 11, 2026 | ||
| Trajectory Classification | AIS Subset | 24 | Jun 11, 2026 | ||
| Long-Form Document-Style Memory Reasoning | MuSiQue | 24 | Jun 11, 2026 | ||
| Long-Form Document-Style Memory Reasoning | 2WikiMultihopQA | 24 | Jun 11, 2026 | ||
| Long-Form Document-Style Memory Reasoning | HotpotQA | 24 | Jun 11, 2026 | ||
| Dialogue-Style Memory Reasoning | PersonaMem | 24 | Jun 11, 2026 | ||
| Dialogue-Style Memory Reasoning | LongMemEval | 24 | Jun 11, 2026 |