Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 991 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Recommendation | Amazon Baby 1-core (test) | 27 | Jun 11, 2026 | ||
| Top-K Recommendation | Amazon Office (test) | 27 | Jun 11, 2026 | ||
| Recommendation | Amazon Music (test) | 27 | Jun 11, 2026 | ||
| Sequential Recommendation | Amazon Fashion | 27 | Jun 11, 2026 | ||
| Sequential Recommendation | Yelp | 27 | Jun 11, 2026 | ||
| Audio-visual target speaker extraction | VoxCeleb-2mix impaired visual scenarios (test) | 27 | Jun 11, 2026 | ||
| Time-series Generation | PEMS08 (Evening Peak) | 27 | Jun 11, 2026 | ||
| Time-series Generation | PEMS08 (Morning Peak) | 27 | Jun 11, 2026 | ||
| Time-series Generation | PEMS04 Evening Peak | 27 | Jun 11, 2026 | ||
| Time-series Generation | Energy (Evening Peak) | 27 | Jun 11, 2026 | ||
| Time Series Generation | PEMS08 | 27 | Jun 11, 2026 | ||
| Time Series Generation | PEMS04 | 27 | Jun 11, 2026 | ||
| PDE Solving | 2D Kuramoto-Sivashinsky (test) | 27 | Jun 11, 2026 | ||
| Code Generation | LiveCodeBench V2 | 27 | Jun 11, 2026 | ||
| Cardiac shape registration | M&M (ED and ES) | 27 | Jun 9, 2026 | ||
| Cardiac shape registration | UK Biobank | 27 | Jun 9, 2026 | ||
| Diagnostic Endpoint Prediction | MIMIC IV | 27 | Jun 9, 2026 | ||
| Exercise Cold Start | XES3G5M | 27 | Jun 9, 2026 | ||
| Exercise Cold Start | NIPS34 | 27 | Jun 9, 2026 | ||
| Time-to-accuracy Language Modeling | GPT-2 Medium (train) | 27 | Jun 9, 2026 | ||
| Quantization latency measurement | NVFP4 quantization operator | 27 | Jun 9, 2026 | ||
| Composed Image Retrieval | ZeroSight | 27 | Jun 8, 2026 | ||
| Image Classification | Flower102 | 27 | Jun 23, 2026 | ||
| Binary-level predictive event coding | AW | 27 | Jun 8, 2026 | ||
| Root-level predictive event coding | PLV | 27 | Jun 8, 2026 |