Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1304 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Underwater Acoustic Classification | VTUAD | 23 | Apr 20, 2026 | ||
| Precipitation Nowcasting | SEVIR (test) | 23 | Jun 9, 2026 | ||
| Domain Reasoning | HL | 23 | Mar 24, 2026 | ||
| Reasoning | SQA | 23 | Mar 24, 2026 | ||
| Algorithmic Reasoning | GSM8K | 23 | Mar 24, 2026 | ||
| Domain Reasoning | Headline | 23 | Mar 24, 2026 | ||
| Domain Reasoning | LB | 23 | Mar 24, 2026 | ||
| Video Generation | VBench | 23 | May 21, 2026 | ||
| Semantic Segmentation | Cityscapes | 23 | Mar 24, 2026 | ||
| Sentiment Classification | Twitter Financial News (test) | 23 | Apr 7, 2026 | ||
| Robot Manipulation | SimplerEnv WidowX | 23 | Jun 11, 2026 | ||
| Image Classification | Waterbirds 95% correlation (test) | 23 | May 13, 2026 | ||
| Few-shot 3D Semantic Segmentation | ScanNet | 23 | Jul 1, 2026 | ||
| Portrait Animation (Self-reenactment) | VFHQ (test) | 23 | Mar 25, 2026 | ||
| Open-Vocabulary Semantic Segmentation | PASCAL VOC-20 (val) | 23 | Jul 7, 2026 | ||
| Text generation | Wikitext-103 | 23 | Apr 14, 2026 | ||
| Few-shot segmentation | FSS-1000 | 23 | Jun 24, 2026 | ||
| Mathematical reasoning | MATH 500 | 23 | Mar 20, 2026 | ||
| Code generation | EvalPlus (test) | 23 | Mar 20, 2026 | ||
| Anti-spoofing | Pooled | 23 | Jul 1, 2026 | ||
| Few-shot Action Recognition | HMDB51 1-shot | 23 | Mar 20, 2026 | ||
| Few-shot Action Recognition | UCF101 1-shot | 23 | Mar 20, 2026 | ||
| Few-shot Action Recognition | Kinetics 1-shot | 23 | Mar 20, 2026 | ||
| Information Retrieval | HotpotQA BEIR | 23 | Jun 16, 2026 | ||
| Function Deletion | HarmfulBench | 23 | Mar 20, 2026 |