Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 464 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Person Re-identification | CCVID General | 45 | Feb 27, 2026 | ||
| Molecular Generation | QM9 | 45 | Jun 8, 2026 | ||
| Anomaly Segmentation | LiverCT | 45 | Feb 26, 2026 | ||
| Medical Visual Question Answering | VQA-RAD closed-end | 45 | Feb 26, 2026 | ||
| Survival Prediction | TCGA-CO-READ (5-fold cross-validation) | 45 | Mar 18, 2026 | ||
| Audio Event Tagging | AudioSet AS-2M (full) | 45 | Mar 5, 2026 | ||
| Sentiment Analysis | IIT-abuse dataset | 44 | Jul 8, 2026 | ||
| Policy Following | POLICYSHIFTBENCH (Adaptive split) | 44 | Jul 8, 2026 | ||
| 3D Point Cloud Semantic Segmentation | ScanNet Average of S0 and S1 | 44 | Jul 1, 2026 | ||
| 3D Few-shot Semantic Segmentation | S3DIS Average | 44 | Jul 1, 2026 | ||
| Trigger Inversion | SST2 | 44 | Jul 1, 2026 | ||
| Trigger inversion | SST2 | 44 | Jul 1, 2026 | ||
| Gene-expression classification | CUMIDA-42 RF-50 + 50 random feature arm headline | 44 | Jun 30, 2026 | ||
| Robotic Video Generation | R-Bench | 44 | Jul 9, 2026 | ||
| Fund sales forecasting | Fund dataset | 44 | Jun 24, 2026 | ||
| Multi-label Classification | reBEN | 44 | Jun 23, 2026 | ||
| Chain-of-Thought Attribution Faithfulness | GSM8K (test) | 44 | Jun 23, 2026 | ||
| Novel View Synthesis | Omni3D | 44 | Jun 19, 2026 | ||
| General Knowledge QA | PIQA | 44 | Jun 15, 2026 | ||
| General Knowledge QA | OBQA | 44 | Jun 15, 2026 | ||
| Image Classification | CIFAR-10 (test) | 44 | Jun 15, 2026 | ||
| Node Classification | Photo semi-supervised (test) | 44 | Jun 23, 2026 | ||
| Retrieval | NIAH seq=4096 | 44 | Jun 9, 2026 | ||
| Uncertainty Estimation | FaceForensics++ (test) | 44 | Jun 8, 2026 | ||
| Constrained Optimization | COCONUT difficult constrained problems | 44 | Jun 5, 2026 |