Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1568 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| OOD Detection | OOD Datasets Mean | 20 | May 11, 2026 | ||
| Full-spectrum Out-of-Distribution Detection | Texture (test) | 20 | May 11, 2026 | ||
| Full-spectrum Out-of-Distribution Detection | SSB Hard (test) | 20 | May 11, 2026 | ||
| mathematical reasoning | AIME 2025 | 20 | May 14, 2026 | ||
| Worst-case Angular Error Estimation | 1 million randomly generated unit vectors | 20 | May 11, 2026 | ||
| Multi-Task Incremental Learning | MTIL few-shot Order II (test) | 20 | May 11, 2026 | ||
| Face generation with Gender alignment | FFHQ | 20 | May 11, 2026 | ||
| Image Generation | Caltech-256 | 20 | May 11, 2026 | ||
| Visual Question Answering | VQA (test) | 20 | May 11, 2026 | ||
| Text Generation | MMLU (test) | 20 | May 11, 2026 | ||
| Image Classification | Fashion-MNIST | 20 | Jul 9, 2026 | ||
| Bike Localization | Customized Dataset (Seen) | 20 | May 11, 2026 | ||
| Image Classification | ImageNet | 20 | May 11, 2026 | ||
| Image Classification | CIFAR-100 | 20 | May 11, 2026 | ||
| Image Classification | ImageNet | 20 | May 11, 2026 | ||
| Image Classification | CIFAR-100 | 20 | May 11, 2026 | ||
| Code Generation | HumanEval | 20 | May 11, 2026 | ||
| Link Prediction | GDELT (Emerging) | 20 | May 11, 2026 | ||
| Link Prediction | ICEWS05-15 (Emerging) | 20 | May 11, 2026 | ||
| Link Prediction | ICEWS 18 (Emerging) | 20 | May 11, 2026 | ||
| Link Prediction | ICEWS14 (Emerging) | 20 | May 11, 2026 | ||
| Medical Diagnosis | AgentClinic OOD original (test) | 20 | May 11, 2026 | ||
| Sequential Recommendation | Google Reviews | 20 | May 11, 2026 | ||
| Decision Reversal Sensitivity Analysis | Diabetes experiment Conditional outcome distributions mu | 20 | May 11, 2026 | ||
| Fixed Response | Fixed Response | 20 | May 8, 2026 |