Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1777 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Predicate Classification | Visual Genome (VG) Zero-Shot | 19 | Feb 26, 2026 | ||
| Sentence-to-Graph Retrieval | Visual Genome Gallery Size 5000 (test) | 19 | Feb 26, 2026 | ||
| Sentence-to-Graph Retrieval | Visual Genome Gallery Size 1000 (test) | 19 | Feb 26, 2026 | ||
| Generalized Object Detection | PASCAL VOC Split 3 | 19 | Feb 27, 2026 | ||
| Generalized Object Detection | PASCAL VOC Split 1 | 19 | Feb 27, 2026 | ||
| Discrete Emotion Recognition | Ravdess 19 (test) | 19 | Feb 26, 2026 | ||
| Discrete Emotion Recognition | CREMA-D 18 (test) | 19 | Feb 26, 2026 | ||
| Linear Probing | Places | 19 | Feb 26, 2026 | ||
| Supporting Fact Prediction | HotpotQA full wiki (dev) | 19 | Feb 26, 2026 | ||
| Retrieval | HotpotQA full wiki (dev) | 19 | Feb 26, 2026 | ||
| Reinforcement Learning | Atari Pong | 19 | Apr 6, 2026 | ||
| Image Dehazing | HSTS RESIDE (test) | 19 | Feb 26, 2026 | ||
| Extractive Question Answering | MRQA | 19 | Feb 26, 2026 | ||
| Word Sense Disambiguation | English All-Words Average (test) | 19 | Feb 27, 2026 | ||
| Word Sense Disambiguation | SemEval Task 13 2015 (test) | 19 | Feb 26, 2026 | ||
| Word Sense Disambiguation | SemEval Task 12 2013 (test) | 19 | Feb 26, 2026 | ||
| Scene Text Recognition | IC03 860 (test) | 19 | Feb 26, 2026 | ||
| Link Prediction | FB122 (test-II) | 19 | Feb 26, 2026 | ||
| Link Prediction | FB122 (test-I) | 19 | Feb 26, 2026 | ||
| Multi-person pose estimation | PoseTrack 2018 (test) | 19 | Feb 26, 2026 | ||
| Aspect-Opinion Pair Extraction | 14res | 19 | Feb 26, 2026 | ||
| Cover Song Identification | Covers80 | 19 | Feb 26, 2026 | ||
| Word Sense Disambiguation | WiC v1.0 (test) | 19 | Feb 26, 2026 | ||
| Salient Object Detection | ViSal | 19 | Feb 26, 2026 | ||
| Salient Object Detection | DAVIS (val) | 19 | Feb 26, 2026 |