Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 2453 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Forensic Detection | FakeClass FakeBench (qualitative setting) | 15 | Mar 17, 2026 | ||
| Parameter Estimation | Engine Gas Flow Dynamics Clean online normalized scale 0-1 (test) | 15 | Mar 17, 2026 | ||
| Anatomy Completion | SkullBreak (test) | 15 | Mar 16, 2026 | ||
| Segmentation | OASIS-4 (test) | 15 | Mar 16, 2026 | ||
| Segmentation | Shenzhen (test) | 15 | Mar 16, 2026 | ||
| Time-series Forecasting | Multi-horizon evaluation 12-Week Horizon | 15 | Mar 16, 2026 | ||
| Time-series Forecasting | Multi-horizon evaluation 6-Week Horizon | 15 | Mar 16, 2026 | ||
| Time-series Forecasting | Multi-horizon evaluation 1-Week Horizon | 15 | Mar 16, 2026 | ||
| Referring Expression Grounding | RefCOCOg | 15 | Jun 8, 2026 | ||
| Autonomous Driving | CARLA Town 2 (test) | 15 | Mar 16, 2026 | ||
| Problem-solving | MATH | 15 | Mar 16, 2026 | ||
| Multiple-choice Question Answering | PubMedQA | 15 | Mar 16, 2026 | ||
| Multiple-choice Question Answering | CFA | 15 | Mar 16, 2026 | ||
| Spectral Risk Optimisation | DGP1 | 15 | Mar 16, 2026 | ||
| Text-to-Image | Pick-a-Pic | 15 | Apr 28, 2026 | ||
| Novel View Synthesis | MIP | 15 | Mar 16, 2026 | ||
| Novel View Synthesis | NS dataset | 15 | Mar 16, 2026 | ||
| Novel View Synthesis | TT dataset | 15 | Mar 16, 2026 | ||
| Flood risk prediction | Kuro Siwo | 15 | Mar 16, 2026 | ||
| Schema retrieval | BIRD | 15 | Mar 16, 2026 | ||
| Class-Incremental Learning | CIFAR-100 5 phases (test) | 15 | Mar 16, 2026 | ||
| Multi-agent Reinforcement Learning | Dectiger | 15 | Mar 16, 2026 | ||
| Multi-agent Reinforcement Learning | Boxpushing | 15 | Mar 16, 2026 | ||
| Semantic Segmentation | SAR One-Domain-Gap (All) | 15 | Mar 13, 2026 | ||
| Semantic Segmentation | SAR One-Domain-Gap (Unseen Complex Value) | 15 | Mar 13, 2026 |