Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 236 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| General Knowledge | MMLU-Pro | 67 | Jul 7, 2026 | ||
| Scientific Reasoning | GPQA Diamond | 67 | Jun 2, 2026 | ||
| Multimodal Evaluation | MME | 67 | May 19, 2026 | ||
| Few-shot 3D Semantic Segmentation | S3DIS (S1) | 67 | Jul 1, 2026 | ||
| Road Extraction | Massachusetts | 67 | Apr 20, 2026 | ||
| Machine Unlearning | TOFU 1.0 (Forget10) | 67 | Jun 29, 2026 | ||
| Depth Estimation | Bonn | 67 | Jun 23, 2026 | ||
| Driver DNF Prediction | Rel F1 | 67 | May 25, 2026 | ||
| Dialogue | MT-Bench | 67 | Jul 1, 2026 | ||
| Reward Modeling | RewardBench v2 (test) | 67 | Apr 28, 2026 | ||
| Mathematical Reasoning | Minerva | 67 | Apr 10, 2026 | ||
| Spatial Reasoning | MMSI-Bench | 67 | Jun 19, 2026 | ||
| Multi-hop QA | 2WikiMultihopQA | 67 | May 13, 2026 | ||
| Language Modeling | LM1B (val) | 67 | May 26, 2026 | ||
| Multi-task Knowledge and Reasoning | MMLU-Pro | 67 | Jun 11, 2026 | ||
| General image understanding | MMStar | 67 | Jul 8, 2026 | ||
| Image Classification | Vision Datasets (14 tasks) 1.0 (test) | 67 | Mar 4, 2026 | ||
| Load forecasting | GEFCom | 67 | Mar 4, 2026 | ||
| Mathematical Reasoning | AMC 2023 | 67 | Mar 24, 2026 | ||
| Visual Question Answering | InfoSeek | 67 | Jul 9, 2026 | ||
| Graph Anomaly Detection | CiteSeer | 67 | Jun 30, 2026 | ||
| Video Understanding | VideoMME | 67 | Jun 30, 2026 | ||
| Surface Normal Estimation | iBims-1 | 67 | Jul 8, 2026 | ||
| Counting | TallyQA | 67 | Jun 2, 2026 | ||
| Fact-based Visual Question Answering | FVQA | 67 | May 12, 2026 |