Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1027 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Optic Cup / Disc Segmentation | Fundus Overall | 27 | Feb 26, 2026 | ||
| Boundary Detection | RoFT original (test) | 27 | Feb 26, 2026 | ||
| Classification | CheXpert 5x200 1.0 | 27 | Feb 26, 2026 | ||
| Classification | RSNA Pneumonia (test) | 27 | Feb 26, 2026 | ||
| Multimodal Understanding | MM-Bench en (test) | 27 | Feb 26, 2026 | ||
| Semantic Segmentation | GTA → Cityscapes (test) | 27 | Feb 26, 2026 | ||
| Automatic Speech Recognition | ATC Corpus | 27 | Feb 26, 2026 | ||
| Action Recognition | NTU RGB+D 60 (55/5) | 27 | May 13, 2026 | ||
| Semantic Segmentation | ScanNet200 v2 (val) | 27 | Feb 26, 2026 | ||
| Referring Segmentation | refCOCOg U (val) | 27 | Jul 8, 2026 | ||
| Anomaly Segmentation | DAGM | 27 | Feb 26, 2026 | ||
| SQL Code Generation | InterCode SQL | 27 | Jun 17, 2026 | ||
| Mathematical Reasoning | Mathematical Tasks GSM8k, MATH, SVAMP, MM | 27 | Feb 26, 2026 | ||
| Multi-Object Tracking | SoccerNet (test) | 27 | Jun 4, 2026 | ||
| Shadow Removal | WSRD+ | 27 | Apr 21, 2026 | ||
| GUI navigation | AITW (test) | 27 | Feb 26, 2026 | ||
| Knowledge Base Question Answering | GrailQA (test) | 27 | Feb 26, 2026 | ||
| Argument Rewriting | Appropriateness Corpus (test) | 27 | Apr 15, 2026 | ||
| Music Genre Classification | GTZAN (test) | 27 | Apr 23, 2026 | ||
| Video Deepfake Detection | DF-TIMIT (test) | 27 | Feb 26, 2026 | ||
| Cross-Task Generalization | Super-NaturalInstructions English Track (unseen clients) | 27 | Feb 26, 2026 | ||
| Text Ranking | BEIR out-of-domain | 27 | Jul 2, 2026 | ||
| Symbolic Reasoning | Coin Flip | 27 | Mar 24, 2026 | ||
| Image Deraining | Average Test100, Test1200, Rain100H, Rain100L (test) | 27 | Jun 23, 2026 | ||
| Interactive Image Segmentation | DAVIS | 27 | Feb 26, 2026 |