Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 2488 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Positive-Unlabeled Learning | SVHN (test) | 15 | Feb 26, 2026 | ||
| Machine Unlearning | CIFAR-10 Random Forget 50% (train) | 15 | Apr 13, 2026 | ||
| Classification | COMPAS | 15 | Feb 26, 2026 | ||
| Classification | German | 15 | Feb 26, 2026 | ||
| Fair Classification | Comm | 15 | Feb 26, 2026 | ||
| Offline-to-Online Reinforcement Learning | D4RL Antmaze | 15 | Feb 26, 2026 | ||
| Offline-to-Online Reinforcement Learning | D4RL Locomotion medium-expert | 15 | Feb 26, 2026 | ||
| Offline-to-Online Reinforcement Learning | D4RL Locomotion medium | 15 | Feb 26, 2026 | ||
| Offline-to-Online Reinforcement Learning | D4RL Locomotion medium-replay | 15 | Feb 26, 2026 | ||
| Offline-to-Online Reinforcement Learning | D4RL Locomotion random | 15 | Feb 26, 2026 | ||
| Logic Recovery | Voltage Regulator System | 15 | Feb 26, 2026 | ||
| Post-training Performance Evaluation | Llama 3.2-3B (val) | 15 | Feb 26, 2026 | ||
| Visual Text Rendering | OCR | 15 | May 11, 2026 | ||
| Regression | 64 Regression Datasets | 15 | Feb 26, 2026 | ||
| Behavior decoding | NHP center-out reaching (test) | 15 | Feb 26, 2026 | ||
| Behavior decoding | NHP grid reaching (test) | 15 | Feb 26, 2026 | ||
| Fraud Detection | CCFRAUD | 15 | Feb 26, 2026 | ||
| Fraud Detection | CCF | 15 | Feb 26, 2026 | ||
| Reasoning Generalization | Out-of-Distribution Avg | 15 | Feb 26, 2026 | ||
| Academic Reasoning | MMLU-Pro | 15 | Feb 26, 2026 | ||
| Open-domain Reasoning | ARC-c | 15 | Feb 26, 2026 | ||
| Scientific and General Reasoning | Nine Competition-level Benchmarks Out-of-Distribution | 15 | Feb 26, 2026 | ||
| Instructional Image Editing | FLUX.1-Kontext | 15 | Feb 26, 2026 | ||
| Anomaly Detection | Average across datasets | 15 | Feb 26, 2026 | ||
| Anomaly Detection | SMAP | 15 | Feb 26, 2026 |