Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 208 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Multimodal Understanding | MMBench (dev) | 73 | Jun 4, 2026 | ||
| Long-context language understanding | LongBench 1.0 (test) | 73 | Jun 9, 2026 | ||
| Multiple-choice Question Answering | MMLU 5-shot | 73 | Apr 2, 2026 | ||
| Moment Retrieval | QVHighlights (val) | 73 | Jun 9, 2026 | ||
| Sentence Classification | SentEval Transfer Tasks (test) | 73 | Feb 26, 2026 | ||
| Targeted Adversarial Attack | ImageNet-Compatible | 73 | Apr 7, 2026 | ||
| Sentiment Classification | SST-5 | 73 | Jun 4, 2026 | ||
| Object Detection | BDD100K (val) | 73 | Jun 24, 2026 | ||
| Object Detection | UAVDT (test) | 73 | Jul 7, 2026 | ||
| Arithmetic Reasoning | SingleEq | 73 | May 27, 2026 | ||
| Audio Classification | ESC50 | 73 | Jun 16, 2026 | ||
| Visual Place Recognition | Pitts 250k (test) | 73 | May 21, 2026 | ||
| Link Prediction | UCI (transductive) | 73 | May 26, 2026 | ||
| Object Detection | Cityscapes -> Foggy Cityscapes | 73 | Mar 20, 2026 | ||
| Sentiment Analysis | IMDB | 73 | May 7, 2026 | ||
| 3D Visual Grounding | Sr3D (test) | 73 | Feb 26, 2026 | ||
| Commonsense Reasoning | PIQA (test) | 73 | Jul 3, 2026 | ||
| Video Action Recognition | HMDB51 (test) | 73 | Feb 26, 2026 | ||
| Offline Reinforcement Learning | D4RL Gym walker2d (medium-replay) | 73 | May 29, 2026 | ||
| Math Word Problem Solving | Math23K (test) | 73 | Feb 26, 2026 | ||
| Abstractive Summarization | SAMSum | 73 | Feb 26, 2026 | ||
| Semantic Segmentation | Pascal-5^i | 73 | Feb 26, 2026 | ||
| Aspect Sentiment Classification | Rest SemEval 2014 (test) | 73 | Apr 16, 2026 | ||
| Form Understanding | FUNSD (test) | 73 | Feb 26, 2026 | ||
| Link Prediction | ICEWS 14 | 73 | Jun 29, 2026 |