Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1790 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Time Series Attribution | ETTh1 | 18 | Jun 29, 2026 | ||
| Remote Sensing Image Change Captioning | Dubai-CC | 18 | Jul 7, 2026 | ||
| Preference Assessment | PickaPic general preference assessment (real-user interaction) | 18 | Jun 29, 2026 | ||
| Preference Assessment | PreferImg MP 1.0 (unseen) | 18 | Jun 29, 2026 | ||
| Preference Assessment | PreferImg SP 1.0 (unseen) | 18 | Jun 29, 2026 | ||
| Preference Assessment | PreferImg MP 1.0 (seen) | 18 | Jun 29, 2026 | ||
| Preference Assessment | PreferImg SP 1.0 (seen) | 18 | Jun 29, 2026 | ||
| Video Matting | VideoMatte | 18 | Jun 26, 2026 | ||
| Span-level detection | Social Media Posts ILE Detection | 18 | Jun 26, 2026 | ||
| Safety Classification | OpenAI Moderation | 18 | Jun 26, 2026 | ||
| Character Role-playing | CharacterEval | 18 | Jun 26, 2026 | ||
| Agentic Image Generation | IA-Bench 1.0 (test) | 18 | Jun 26, 2026 | ||
| Spoken Term Detection | LibriSpeech Out-of-Vocabulary queries train-clean-100 | 18 | Jun 26, 2026 | ||
| Spoken Term Detection | LibriSpeech train-clean-100 (In-Vocabulary queries) | 18 | Jun 26, 2026 | ||
| Lattice Reduction | Subset Sum instances bit-length 40 | 18 | Jun 26, 2026 | ||
| Visual Search Prediction | Visual Search Experiment Human vs Model comparison 1.0 | 18 | Jun 26, 2026 | ||
| Abstract Reasoning | ARC-AGI 2 | 18 | Jun 26, 2026 | ||
| Abstract Reasoning | ARC-AGI 1 | 18 | Jun 26, 2026 | ||
| Image Restoration | Tiles Severe | 18 | Jun 26, 2026 | ||
| Image Restoration | Pterois Medium | 18 | Jun 26, 2026 | ||
| Image Restoration | Jellyfish Mild | 18 | Jun 26, 2026 | ||
| Route Recommendation | Mobility | 18 | Jun 26, 2026 | ||
| Route Recommendation | Employment | 18 | Jun 26, 2026 | ||
| Route Recommendation | TravelTime | 18 | Jun 26, 2026 | ||
| Route Recommendation | Income | 18 | Jun 26, 2026 |