Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 2227 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Knowledge Unlearning | FaithUn | 16 | Mar 5, 2026 | ||
| Offline Video Understanding | VideoMME w/o sub. | 16 | Mar 4, 2026 | ||
| Material Property Prediction | Matminer Dielectric Constant 5-split average | 16 | Apr 28, 2026 | ||
| Visual Question Answering | LingoQA | 16 | Mar 4, 2026 | ||
| Map-based Language Modeling | MAPLM | 16 | Mar 4, 2026 | ||
| Interactive Recommendation | KuaiRec Max Len 30 | 16 | Mar 4, 2026 | ||
| Automated Algorithm Design | ASP | 16 | May 20, 2026 | ||
| Problem Generation | KMP-Skills | 16 | Mar 4, 2026 | ||
| Error Detection and Correction | KMP-Skills | 16 | Mar 4, 2026 | ||
| Locomotion | MuJoCo Walker2d Medium-Replay D4RL | 16 | May 15, 2026 | ||
| 3D human reconstruction | THuman 2.1 (test) | 16 | Apr 14, 2026 | ||
| Response Classification | Public Safety Benchmarks Response Suite | 16 | Mar 4, 2026 | ||
| Point map estimation | Average | 16 | May 29, 2026 | ||
| Mesh Reconstruction | Toys4K | 16 | Mar 12, 2026 | ||
| RGB-Thermal Tracking | RGBT234 | 16 | Mar 4, 2026 | ||
| Video Reasoning | SEED-Bench L3 OOD R1 | 16 | Mar 4, 2026 | ||
| Video Reasoning | SEED-Bench L2 OOD R1 | 16 | Mar 4, 2026 | ||
| Video Reasoning | SEED-Bench-R1 L1 In-Dist. | 16 | Mar 4, 2026 | ||
| Prompt Moderation | FlexBench | 16 | Mar 4, 2026 | ||
| Verilog Code Generation | RTLLM v1 | 16 | Mar 4, 2026 | ||
| Coronary Artery Segmentation | Coronary artery segmentation dataset (5-fold cross-val) | 16 | Mar 4, 2026 | ||
| Visual Question Answering | GQA | 16 | Mar 4, 2026 | ||
| Multimodal Mathematical Reasoning | MathVerse (testmini) | 16 | Mar 4, 2026 | ||
| Reasoning | AQuA, MMLU, StrategyQA, and CommonSenseQA Average | 16 | Mar 4, 2026 | ||
| Mathematical Reasoning | AQuA | 16 | Mar 4, 2026 |