Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1615 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Image-to-Text Retrieval | MIMIC-CXR (test) | 20 | Mar 23, 2026 | ||
| Traveling Salesman Problem with Time Windows | TSPTW hard variant (n=50) | 20 | Feb 26, 2026 | ||
| Lossy Data Compression | Seashell | 20 | Feb 26, 2026 | ||
| Lossy Data Compression | Pine Cone | 20 | Feb 26, 2026 | ||
| Lossy Data Compression | Walnuts | 20 | Feb 26, 2026 | ||
| Lossy Data Compression | Chicken | 20 | Feb 26, 2026 | ||
| Lossy Data Compression | Ryugu | 20 | Feb 26, 2026 | ||
| Lossy Data Compression | Fossil | 20 | Feb 26, 2026 | ||
| Lossy Data Compression | Wood | 20 | Feb 26, 2026 | ||
| Output Diversity | MT-Bench | 20 | Feb 26, 2026 | ||
| Dynamic Novel View Synthesis | DyCheck 5 scenes 1.0 | 20 | Jun 30, 2026 | ||
| Classification | Thyroid abnormality tabular dataset (test) | 20 | Feb 26, 2026 | ||
| Agentic | τ2-Bench | 20 | Jul 7, 2026 | ||
| Binary Classification | Tadpole CN vs MCI (test) | 20 | Feb 26, 2026 | ||
| Binary classification (CN vs MCI) | NACC | 20 | Feb 26, 2026 | ||
| Audio Inpainting | MusicNet (test) | 20 | Feb 26, 2026 | ||
| Fairness-aware Sum-rate Maximization | Downlink MISO channel simulation (test) | 20 | Feb 26, 2026 | ||
| Polyp Segmentation | PolypGen Data Centre 2 | 20 | Mar 10, 2026 | ||
| Robustness against priming vulnerability | JBB-Behaviors (test) | 20 | Feb 26, 2026 | ||
| Veracity Inference | COMMONSENSEQA 1,000 examples | 20 | Feb 26, 2026 | ||
| Veracity Inference | GSM8K 1,000 examples | 20 | Feb 26, 2026 | ||
| Veracity Inference | PRONTOQA (1,000 examples) | 20 | Feb 26, 2026 | ||
| Mortality prediction | MIMIC-III | 20 | Mar 26, 2026 | ||
| window-open | Meta-World window-open | 20 | May 22, 2026 | ||
| window-close | Meta-World window-close | 20 | May 22, 2026 |