Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 486 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Intrusion Detection | Edge-IIoTset (test) | 43 | Jun 11, 2026 | ||
| Min-cost flow | Escape routing (test) | 43 | Feb 26, 2026 | ||
| Zero-shot Commonsense Reasoning | ARC-Easy, ARC-Challenge, HellaSwag, PIQA, WinoGrande lm-evaluation-harness (test) | 43 | May 13, 2026 | ||
| Machine Unlearning | Tiny-ImageNet (train) | 43 | Mar 30, 2026 | ||
| Machine Unlearning | TOFU | 43 | Feb 26, 2026 | ||
| Common Sense Reasoning | ARC-Easy (ARC-E) 0-shot | 43 | Jun 26, 2026 | ||
| Graph Classification | Mutagenicity Edge Shift M0→M2 | 43 | Apr 6, 2026 | ||
| Time Series Anomaly Detection | SWAN | 43 | Jun 18, 2026 | ||
| Time Series Anomaly Detection | SWaT | 43 | Jun 18, 2026 | ||
| Code Analysis | LongBench | 43 | Mar 13, 2026 | ||
| Synthetic Tasks | LongBench | 43 | Mar 13, 2026 | ||
| OOD detection | Cora | 43 | May 14, 2026 | ||
| Sequential Recommendation | Sports | 43 | Feb 26, 2026 | ||
| Next-POI Recommendation | TKY (test) | 43 | Apr 24, 2026 | ||
| Trajectory planning | NAVSIM v2 (navhard) | 43 | Jun 1, 2026 | ||
| Visual Question Answering | Chest X-ray VQA (test) | 43 | Feb 26, 2026 | ||
| Object Hallucination Evaluation | GQA (Random) | 43 | Jun 30, 2026 | ||
| Object Hallucination Evaluation | MSCOCO (Random) | 43 | Jun 30, 2026 | ||
| Multimodal Reasoning | MMMU (test) | 43 | Jun 30, 2026 | ||
| Mathematical Reasoning | MathVista | 43 | Mar 25, 2026 | ||
| Image Reconstruction | ImageNet 256x256 2012 (val) | 43 | May 8, 2026 | ||
| Image Pointing | Point-Bench | 43 | May 5, 2026 | ||
| Video Counting | Molmo2 VideoCount (val) | 43 | Mar 31, 2026 | ||
| Video Captioning | Molmo2 CapTest (test) | 43 | Mar 31, 2026 | ||
| Video Understanding | Tomato (test) | 43 | Mar 31, 2026 |