Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1523 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Multi-task Regression | MovieLens (test) | 21 | Feb 26, 2026 | ||
| Long-term forecasting | ETTm1 v1 (test) | 21 | Feb 26, 2026 | ||
| De Novo Generation | MP-20 | 21 | Apr 3, 2026 | ||
| Stable structure prediction | Carbon-24 | 21 | Apr 14, 2026 | ||
| Blind Docking | PDBBind Apo ESMFold proteins generated (test) | 21 | Feb 26, 2026 | ||
| Signed Link Prediction | Epinions (test) | 21 | Jun 5, 2026 | ||
| Signed Link Prediction | Slashdot (test) | 21 | Jun 5, 2026 | ||
| Signed Link Prediction | Bitcoin-Alpha (test) | 21 | Feb 26, 2026 | ||
| Speech Dereverberation | WSJ0-Reverb (test) | 21 | Mar 20, 2026 | ||
| Image Classification | NIH ChestX-ray | 21 | Feb 27, 2026 | ||
| User-Generated Content Video Quality Assessment | KonViD 1k (test) | 21 | Feb 26, 2026 | ||
| Classification | MSCOCO-GLT (ALT protocol) | 21 | Feb 26, 2026 | ||
| Classification | MSCOCO (GLT protocol) | 21 | Feb 26, 2026 | ||
| Classification | MSCOCO-GLT (CLT protocol) | 21 | Feb 26, 2026 | ||
| Image Classification | ImageNet-GLT GBL 1k (test) | 21 | Feb 26, 2026 | ||
| Hand gesture recognition | EgoGesture (test) | 21 | Feb 26, 2026 | ||
| Image Classification | ImageNet 1% labeled 1.0 | 21 | Feb 26, 2026 | ||
| Multimodal Understanding | MMVet v2 (0613) | 21 | Feb 27, 2026 | ||
| Multimodal Multilingual Evaluation | MMBench Multilingual | 21 | Feb 27, 2026 | ||
| Multi-task Code Intelligence (Overall) | CodefuseEval and CodeXGLUE | 21 | Feb 26, 2026 | ||
| Defect Detection | CodeXGLUE | 21 | Feb 26, 2026 | ||
| Code Repair | CodeXGLUE | 21 | Feb 26, 2026 | ||
| Clone Detection | CodeXGLUE | 21 | Feb 26, 2026 | ||
| Code Translation | CodefuseEval | 21 | Feb 26, 2026 | ||
| Sparse-View CT Reconstruction | AAPM Sagittal View (test) | 21 | Feb 26, 2026 |