Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 625 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| 3D occupancy prediction | Occ3D nuScenes | 36 | Jun 23, 2026 | ||
| Question Answering | LoCoMo | 36 | Jun 23, 2026 | ||
| Regression | Regression streams with controlled distribution shift | 36 | Jun 23, 2026 | ||
| Regression | Regression Tasks under Controlled Distribution Shift | 36 | Jun 23, 2026 | ||
| Regression | Regression Tasks | 36 | Jun 23, 2026 | ||
| Privacy-Aware Response Generation | PrivacyAlign (test) | 36 | Jun 23, 2026 | ||
| Square | MimicGen D2 | 36 | Jun 19, 2026 | ||
| Stochastic Orienteering | TSPLIB Real-world graphs 95 | 36 | Jun 18, 2026 | ||
| Time-series Forecasting | ECL | 36 | Jun 17, 2026 | ||
| Time-series forecasting | Synthetic Low Entropy Periodic | 36 | Jun 17, 2026 | ||
| Time-series forecasting | Synthetic High Entropy Periodic | 36 | Jun 17, 2026 | ||
| Time-Series Forecasting | Jena Climate | 36 | Jun 17, 2026 | ||
| Two-sample testing | thyroid | 36 | Jun 16, 2026 | ||
| Two-sample testing | loan | 36 | Jun 16, 2026 | ||
| Two-sample testing | covertype | 36 | Jun 16, 2026 | ||
| Two-sample testing | adult | 36 | Jun 16, 2026 | ||
| Two-sample Testing | Yearbook 1955-1974 vs 1975-1994 original (test) | 36 | Jun 16, 2026 | ||
| Prompt Injection Defense | AgentDojo R1–R3 | 36 | Jun 16, 2026 | ||
| Motion Forecasting | Argoverse 2 (test) | 36 | Jun 16, 2026 | ||
| Membership Inference Attack | Maths & College Reasoning | 36 | Jun 16, 2026 | ||
| Membership Inference Attack | CAMEL Math Reasoning | 36 | Jun 16, 2026 | ||
| Membership Inference Attack | Medical-o1 reasoning-SFT | 36 | Jun 16, 2026 | ||
| Text-to-Image Generation | prompts 500 sampled | 36 | Jun 15, 2026 | ||
| Reasoning | AIME 120 | 36 | Jun 12, 2026 | ||
| Commonsense Reasoning | ARC-C | 36 | Jul 8, 2026 |