Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 2164 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Machine Unlearning | MUSE forget-set | 16 | May 15, 2026 | ||
| Knowledge Retention | WMDP cyber (retain) | 16 | May 15, 2026 | ||
| Machine Unlearning | WMDP-cyber forget-set | 16 | May 15, 2026 | ||
| Knowledge Retention | WMDP-chem (retain) | 16 | May 15, 2026 | ||
| Machine Unlearning | WMDP chem forget-set | 16 | May 15, 2026 | ||
| Knowledge Retention | WMDP bio (retain) | 16 | May 15, 2026 | ||
| Machine Unlearning | WMDP-bio (forget-set) | 16 | May 15, 2026 | ||
| Structural Erasure | MUSE | 16 | May 15, 2026 | ||
| Structural Erasure | WMDP-cyber | 16 | May 15, 2026 | ||
| Structural Erasure | WMDP chem | 16 | May 15, 2026 | ||
| Structural Erasure | WMDP bio | 16 | May 15, 2026 | ||
| Video Moment Retrieval | Charades | 16 | May 15, 2026 | ||
| RSRP Prediction | DTU RSRP | 16 | May 15, 2026 | ||
| Language Understanding and Reasoning | General Capability Suite (MMLU, TruthfulQA, HellaSwag, ARC-Easy) (test) | 16 | May 15, 2026 | ||
| Inference Throughput | GPT-J 6B | 16 | May 15, 2026 | ||
| Policy Synthesis | Grid-world | 16 | May 15, 2026 | ||
| Machine Unlearning | Unlearning Evaluation Suite | 16 | May 15, 2026 | ||
| Machine Unlearning | Aggregate CIFAR-10, Food, STL, ObjectNet, ImageNet | 16 | May 15, 2026 | ||
| Closed-loop Planning | Bench2Drive Base set | 16 | May 15, 2026 | ||
| Few-shot classification | FC100 | 16 | May 15, 2026 | ||
| Continual Test-Time Adaptation | CIN-C (corr split) | 16 | May 15, 2026 | ||
| Continual Test-Time Adaptation | CIN-C iid | 16 | May 15, 2026 | ||
| Image Classification | CCC Hard | 16 | May 15, 2026 | ||
| Image Classification | CCC Medium | 16 | May 15, 2026 | ||
| Image Classification | CCC Easy | 16 | May 15, 2026 |