Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1909 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| OOD detection | ogbn-arxiv | 18 | May 13, 2026 | ||
| Safety Alignment | StrongReject | 18 | May 4, 2026 | ||
| Recommendation | ML-100K | 18 | Feb 26, 2026 | ||
| Boolean Matrix Factorization | Small dataset | 18 | Feb 26, 2026 | ||
| Federated Recommendation | Movie | 18 | Feb 27, 2026 | ||
| Federated Recommendation | Dance | 18 | Feb 27, 2026 | ||
| Federated Recommendation | Food | 18 | Feb 27, 2026 | ||
| Federated Recommendation | KU | 18 | Feb 27, 2026 | ||
| Rating Prediction | MovieLens | 18 | Jun 2, 2026 | ||
| Cognitive Diagnosis | SLP-Math (80%/10%/10%) | 18 | Feb 26, 2026 | ||
| Cognitive Diagnosis | SLP-Math (70%/10%/20%) | 18 | Feb 26, 2026 | ||
| Cognitive Diagnosis | SLP-Math (60% 20% 20%) | 18 | Feb 26, 2026 | ||
| Cognitive Diagnosis | SLP-Math (50%/20%/30%) | 18 | Feb 26, 2026 | ||
| Cognitive Diagnosis | ASSIST09 (80%/10%/10%) | 18 | Feb 26, 2026 | ||
| Cognitive Diagnosis | ASSIST09 (70%/10%/20%) | 18 | Feb 26, 2026 | ||
| Cognitive Diagnosis | ASSIST09 (60%/20%/20%) | 18 | Feb 26, 2026 | ||
| Cognitive Diagnosis | ASSIST09 (50%/20%/30%) | 18 | Feb 26, 2026 | ||
| Learner Performance Prediction | SLP-Math | 18 | Feb 26, 2026 | ||
| Recommendation | Movies & TV | 18 | Feb 26, 2026 | ||
| Sequential Recommendation | Arts | 18 | Mar 30, 2026 | ||
| Sequential Recommendation | Home | 18 | Feb 26, 2026 | ||
| Question Answering | Combined 7 Datasets | 18 | Feb 26, 2026 | ||
| Sequential Recommendation | Amazon Industrial and Scientific (test) | 18 | Mar 25, 2026 | ||
| Retrieval-Augmented Generation | Average | 18 | Feb 26, 2026 | ||
| Retrieval-Augmented Generation | UltraDomain mix | 18 | Feb 26, 2026 |