Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 247 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Visual Place Recognition | Eynsham | 66 | Apr 27, 2026 | ||
| Paraphrase Identification | PAWS-X | 66 | Apr 15, 2026 | ||
| Imputation | Facial expression dataset MCAR | 65 | Jul 7, 2026 | ||
| Data Imputation | Energy dataset MNAR | 65 | Jul 7, 2026 | ||
| Data Imputation | Energy dataset MAR | 65 | Jul 7, 2026 | ||
| Data Imputation | Energy dataset MCAR | 65 | Jul 7, 2026 | ||
| Data Imputation | energy MNAR | 65 | Jul 7, 2026 | ||
| Data Imputation | energy MAR | 65 | Jul 7, 2026 | ||
| Data Imputation | energy MCAR | 65 | Jul 7, 2026 | ||
| Uncertainty Estimation | AOKVQA | 65 | Jul 1, 2026 | ||
| Inter-robot pose estimation | Real-world experiments (Exp. 01 - Exp. 13) | 65 | Jun 26, 2026 | ||
| Prognostics | Unibo | 65 | Jun 5, 2026 | ||
| Text reconstruction | Zhihu answers | 65 | May 29, 2026 | ||
| Zero-shot text reconstruction | Chinese official news text n=200 chunks (test) | 65 | May 29, 2026 | ||
| Text reconstruction | Chinese Wikipedia n = 200 (test) | 65 | May 29, 2026 | ||
| Multi-label Recognition | PASCAL VOC 2012 | 65 | Jun 12, 2026 | ||
| Beam Tracking | Beam Tracking Simulation | 65 | May 22, 2026 | ||
| Zero-shot Reasoning | 9 Common Sense Reasoning Tasks (WinoGrande, SocialIQA, LAMBADA, MMLU, ARC-Easy, ARC-Challenge, HellaSwag, OpenBookQA, PIQA) Average | 65 | May 12, 2026 | ||
| Long-term conversational memory | LoCoMo | 65 | Jun 16, 2026 | ||
| Node Classification | Actor L=2 (test) | 65 | May 12, 2026 | ||
| Instruction Following | ALFWorld (val seen) | 65 | Jun 19, 2026 | ||
| Mathematical Optimization Solving | ComplexLP | 65 | Jun 29, 2026 | ||
| Point Cloud Registration | C3DLM | 65 | Apr 21, 2026 | ||
| Science Reasoning | ARC-C | 65 | Jun 16, 2026 | ||
| Text-to-Image Generation | Paintings category | 65 | Apr 21, 2026 |